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. 4367
    Prev
    Next
    INDEX
    Explanations

    phrases related to delivering something successfully

    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
    +0.23
    1.1%
    59
    +0.13
    0.6%
    167
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.23
    0.24
    393
    +0.13
    0.24
    59
    +0.12
    0.07
    Negative Logits
    pmwiki
    -0.84
    wikipedia
    -0.79
    bi
    -0.72
    zai
    -0.70
    conn
    -0.68
    FactoryReloaded
    -0.68
    bes
    -0.68
    Du
    -0.66
    col
    -0.66
    wart
    -0.63
    POSITIVE LOGITS
     delivered
    0.84
    ragon
    0.79
     deliver
    0.78
    icts
    0.78
    Delivery
    0.77
     delivery
    0.77
     Delivery
    0.75
    ables
    0.75
    loads
    0.75
     delivering
    0.74
    Activations Density 12.154%

    No Known Activations