© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 40432
    Prev
    Next
    INDEX
    Explanations

    phrases related to trademarks and intellectual property

    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
    +0.15
    0.8%
    609
    +0.10
    0.5%
    288
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.26
    326
    +0.10
    0.23
    403
    +0.09
    0.06
    Negative Logits
    heed
    -0.82
    adra
    -0.77
    inth
    -0.76
    ationally
    -0.74
    à¥
    -0.71
    sis
    -0.71
    adi
    -0.70
    erves
    -0.69
    eth
    -0.69
    indust
    -0.69
    POSITIVE LOGITS
     Hallow
    0.66
    ries
    0.62
     characteristics
    0.61
     deviation
    0.60
     trademark
    0.59
    eatures
    0.57
     Style
    0.56
     hallmark
    0.56
     Cutter
    0.56
     pronunciation
    0.55
    Activations Density 8.267%

    No Known Activations