© 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. 11743
    Prev
    Next
    INDEX
    Explanations

    verbs related to leadership or guidance

    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
    679
    +0.17
    0.6%
    183
    +0.14
    0.5%
    176
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.17
    0.05
    164
    +0.14
    0.05
    185
    +0.14
    0.05
    Negative Logits
    pload
    -0.99
    ombies
    -0.97
    atoes
    -0.93
     Scotia
    -0.91
    pton
    -0.90
    entric
    -0.90
    atron
    -0.88
    rehens
    -0.87
    arest
    -0.85
    mma
    -0.84
    POSITIVE LOGITS
    ership
    1.41
    gers
    1.37
    better
    1.31
    quartered
    1.23
    gest
    1.19
    ges
    1.12
    gling
    1.09
    boards
    1.07
    ging
    1.06
    lines
    1.04
    Activations Density 0.968%

    No Known Activations