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. 4385
    Prev
    Next
    INDEX
    Explanations

    reports of deaths or fatal incidents related to various causes and circumstances

    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
    +0.16
    0.8%
    727
    +0.12
    0.6%
    420
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.16
    0.30
    393
    +0.12
    0.32
    375
    +0.09
    0.06
    Negative Logits
    soDeliveryDate
    -0.81
    soType
    -0.77
    eele
    -0.72
    Union
    -0.66
    Enabled
    -0.65
    Grab
    -0.65
    oyer
    -0.64
    ATT
    -0.64
    NESS
    -0.63
    provided
    -0.62
    POSITIVE LOGITS
     gunshot
    0.92
     overdose
    0.92
     childbirth
    0.89
     overdoses
    0.86
     illness
    0.85
     leukemia
    0.84
     suicide
    0.82
     poisoning
    0.82
     tuberculosis
    0.79
    ukemia
    0.79
    Activations Density 16.757%

    No Known Activations