© 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 EvalsExportsinterp-engineNEWAPI 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. 7462
    Prev
    Next
    INDEX
    Explanations

    language related to making decisions or having options to choose from

    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
    +0.17
    0.5%
    276
    +0.17
    0.5%
    754
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.17
    0.05
    754
    +0.17
    0.04
    540
    +0.17
    0.05
    Negative Logits
    uum
    -1.29
    awar
    -1.20
    brance
    -1.17
    vae
    -1.11
    monton
    -1.08
    zona
    -1.03
    peria
    -1.02
    amen
    -1.02
    velop
    -1.02
    monds
    -1.01
    POSITIVE LOGITS
     choices
    1.48
    axe
    1.29
     choice
    1.26
     ACTIONS
    1.08
     options
    1.07
    éĹĺ
    1.07
     axe
    1.06
    Choice
    1.01
     chose
    1.01
    choice
    1.00
    Activations Density 0.605%

    No Known Activations