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. 34628
    Prev
    Next
    INDEX
    Explanations

    code snippets related to complex mathematical operations and functions

    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
    +0.12
    0.7%
    442
    +0.10
    0.5%
    146
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    114
    +0.12
    0.06
    283
    +0.10
    0.01
    178
    +0.09
    0.10
    Negative Logits
    worm
    -0.65
    worms
    -0.63
    agos
    -0.60
    idem
    -0.58
    ngth
    -0.58
     coron
    -0.56
    ifying
    -0.55
    azon
    -0.55
    assic
    -0.55
    entary
    -0.54
    POSITIVE LOGITS
    )))
    0.81
    println
    0.74
    ))
    0.73
     âĩ
    0.69
    ))))
    0.67
     Âł Âł Âł Âł Âł Âł Âł Âł
    0.66
     actionGroup
    0.65
    ption
    0.65
    IELD
    0.64
    )]
    0.64
    Activations Density 4.279%

    No Known Activations