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

    Neuronpedia

    Jacobian LensNEW
    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. 12157
    Prev
    Next
    INDEX
    Explanations

    phrases related to music and cultural events

    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
    637
    +0.17
    0.6%
    527
    +0.13
    0.5%
    763
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.17
    0.04
    284
    +0.13
    0.05
    556
    +0.13
    0.04
    Negative Logits
    peria
    -0.76
     cannibal
    -0.74
    inki
    -0.70
     Lanka
    -0.69
     matter
    -0.69
    ournals
    -0.69
     slash
    -0.68
     Aden
    -0.67
     superst
    -0.67
     Rue
    -0.66
    POSITIVE LOGITS
    odox
    1.27
    iculture
    1.02
    ocene
    0.98
    quer
    0.95
    emort
    0.93
    ĺħ
    0.93
    ements
    0.92
    ypes
    0.91
    icular
    0.89
    iot
    0.88
    Activations Density 0.600%

    No Known Activations