© 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. 12634
    Prev
    Next
    INDEX
    Explanations

    family relationships and connections between individuals

    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
    288
    +0.16
    0.6%
    383
    +0.14
    0.5%
    35
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    610
    +0.16
    0.04
    555
    +0.14
    0.04
    701
    +0.13
    0.04
    Negative Logits
    ilitarian
    -0.99
     constitu
    -0.98
    tering
    -0.95
    etting
    -0.94
    CAST
    -0.94
    psey
    -0.93
    eh
    -0.93
     moot
    -0.87
    enhagen
    -0.86
    OME
    -0.86
    POSITIVE LOGITS
    Maria
    1.05
     Bei
    1.04
     Ivanka
    1.01
     Isabel
    0.96
    wife
    0.95
     daughter
    0.94
    hood
    0.91
    ILY
    0.91
     Louise
    0.89
     panties
    0.86
    Activations Density 0.584%

    No Known Activations