© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 14270
    Prev
    Next
    INDEX
    Explanations

    information related to sports and politics

    oai_token-act-pair · gpt-3.5-turbo

    special characters, specifically the sequences "âĢ" and "Ļ"

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    552
    +0.10
    0.5%
    514
    +0.10
    0.4%
    151
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.10
    0.26
    154
    +0.10
    0.25
    514
    +0.10
    0.20
    Negative Logits
     guiActiveUnfocused
    -0.76
     Nib
    -0.76
     Slug
    -0.70
    ozy
    -0.69
    osate
    -0.69
     Naz
    -0.68
     Niet
    -0.66
     scattering
    -0.66
     shack
    -0.66
     Ukrain
    -0.66
    POSITIVE LOGITS
    should
    1.02
    £
    1.02
    perhaps
    1.01
    sure
    0.97
    ¡
    0.95
    agree
    0.93
    Ĵ
    0.89
    especially
    0.89
    yet
    0.88
    ¹
    0.86
    Activations Density 1.355%

    No Known Activations