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

    Neuronpedia

    APICircuit 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. 40271
    Prev
    Next
    INDEX
    Explanations

    political and legal terms

    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
    36
    +0.28
    1.2%
    393
    +0.26
    1.1%
    447
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.28
    0.37
    393
    +0.26
    0.24
    159
    +0.17
    0.17
    Negative Logits
    Rules
    -0.85
    marks
    -0.83
    via
    -0.81
    Cho
    -0.78
    vine
    -0.76
    agree
    -0.74
    upon
    -0.74
    Enjoy
    -0.73
    flows
    -0.73
    Engine
    -0.73
    POSITIVE LOGITS
     sake
    1.42
     multitude
    1.16
     foreseeable
    1.15
     glimpse
    1.02
     variety
    1.01
     whopping
    1.00
     bunch
    0.99
     couple
    0.99
    ummies
    0.97
     handful
    0.97
    Activations Density 6.668%

    No Known Activations