© 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. 12921
    Prev
    Next
    INDEX
    Explanations

    verbs associated with the concept of realizing or coming to an understanding

    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
    +0.31
    1.4%
    288
    +0.15
    0.7%
    642
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.31
    0.30
    213
    +0.15
    0.10
    635
    +0.13
    0.10
    Negative Logits
    ĪĴ
    -0.89
    picking
    -0.76
    oil
    -0.68
    cgi
    -0.67
    pour
    -0.65
     injunction
    -0.65
    reen
    -0.64
    agues
    -0.64
     helmets
    -0.64
    wra
    -0.64
    POSITIVE LOGITS
    ledged
    0.86
     how
    0.81
    REAM
    0.79
    ibility
    0.76
    âĶģ
    0.76
     realize
    0.75
    urities
    0.75
     realizes
    0.72
     WHY
    0.71
     realise
    0.71
    Activations Density 11.498%

    No Known Activations