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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 39864
    Prev
    Next
    INDEX
    Explanations

    words related to problem-solving and decision-making in technical contexts

    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
    447
    +0.24
    1.1%
    105
    +0.13
    0.6%
    665
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.24
    0.22
    570
    +0.13
    0.04
    764
    +0.11
    0.11
    Negative Logits
    Downloadha
    -0.69
     Latter
    -0.65
    ¥µ
    -0.63
    Org
    -0.63
    emale
    -0.62
    alde
    -0.61
    cade
    -0.61
     Holo
    -0.61
    catentry
    -0.60
    ankind
    -0.59
    POSITIVE LOGITS
     manually
    0.84
    escription
    0.76
     oneself
    0.74
     urgently
    0.74
     ASAP
    0.69
     somewhere
    0.66
     scram
    0.66
     lengths
    0.64
     backup
    0.63
    ordinate
    0.63
    Activations Density 13.573%

    No Known Activations