Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 34250
    Prev
    Next
    INDEX
    Explanations

    numerical ranges and technical terms related to technology and science

    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
    +0.19
    0.8%
    290
    +0.17
    0.7%
    420
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    290
    +0.19
    0.09
    260
    +0.17
    0.09
    616
    +0.13
    0.07
    Negative Logits
    ysis
    -0.95
    iple
    -0.91
     parted
    -0.81
     redes
    -0.80
    zzy
    -0.79
    iane
    -0.77
     Berm
    -0.76
    oller
    -0.74
    orno
    -0.73
    enture
    -0.72
    POSITIVE LOGITS
    20439
    0.96
    specific
    0.95
    micro
    0.95
    _>
    0.94
    advertising
    0.93
    coll
    0.92
    cases
    0.90
    bury
    0.88
    double
    0.87
    craft
    0.86
    Activations Density 5.657%

    No Known Activations