© 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 Local
    9. 6-RES_SCL-AJT
    11. 31818
    Prev
    Next
    INDEX
    Explanations

    verbs related to achieving or carrying out tasks or goals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    151
    +0.10
    0.5%
    447
    +0.10
    0.5%
    728
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.20
    151
    +0.10
    0.15
    728
    +0.09
    0.05
    Negative Logits
    lights
    -0.64
    creen
    -0.61
    reen
    -0.59
    otin
    -0.58
    asio
    -0.57
    lar
    -0.56
    osate
    -0.56
    planet
    -0.56
    )=(
    -0.56
    ril
    -0.56
    POSITIVE LOGITS
    issance
    0.76
    ments
    0.74
    女
    0.67
     accomplish
    0.66
    ment
    0.65
     diligence
    0.60
    NESS
    0.57
    INGS
    0.57
     endeavors
    0.57
     wonders
    0.57
    Activations Density 7.651%

    No Known Activations