© 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. 39890
    Prev
    Next
    INDEX
    Explanations

    words related to community programs, projects, and organizations

    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
    99
    +0.14
    0.6%
    608
    +0.13
    0.6%
    302
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.16
    99
    +0.13
    0.09
    247
    +0.13
    0.07
    Negative Logits
    Downloadha
    -1.13
    thing
    -0.95
    ames
    -0.92
    vati
    -0.91
    gered
    -0.88
    otomy
    -0.85
    inx
    -0.84
    nings
    -0.81
    manship
    -0.80
    ftime
    -0.80
    POSITIVE LOGITS
     Territories
    1.08
     Rating
    0.96
     Spaces
    0.95
     Sever
    0.93
     Connection
    0.93
     Disorder
    0.92
    ité
    0.91
     Improvement
    0.91
     Solutions
    0.91
     Services
    0.90
    Activations Density 4.403%

    No Known Activations