© 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. 14263
    Prev
    Next
    INDEX
    Explanations

    explanations or justifications for actions or beliefs

    oai_token-act-pair · gpt-3.5-turbo
    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
    393
    +0.19
    0.6%
    679
    +0.16
    0.5%
    57
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.19
    0.04
    504
    +0.16
    0.04
    236
    +0.14
    0.05
    Negative Logits
     Roller
    -1.19
    ymph
    -1.14
    lator
    -1.00
    ister
    -0.99
    ãĤ¤ãĥĪ
    -0.99
    gets
    -0.96
    aughed
    -0.95
    shaw
    -0.94
    phrine
    -0.93
    room
    -0.92
    POSITIVE LOGITS
     why
    1.30
    soever
    1.28
     WHY
    1.11
    why
    1.05
     exactly
    0.95
    abouts
    0.93
     prompted
    0.91
     people
    0.90
     justifying
    0.89
    soType
    0.87
    Activations Density 0.669%

    No Known Activations