© 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. 34792
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Watson"

    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
    +0.13
    0.7%
    288
    +0.10
    0.5%
    644
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.12
    288
    +0.10
    0.22
    277
    +0.09
    0.06
    Negative Logits
    erie
    -0.62
    Ľ
    -0.60
     painter
    -0.59
    cephal
    -0.59
     fixation
    -0.55
    arching
    -0.55
    rete
    -0.55
    ulatory
    -0.55
    ories
    -0.54
    ths
    -0.54
    POSITIVE LOGITS
    ihara
    0.65
    combe
    0.65
    enegger
    0.63
    tsky
    0.62
     Watson
    0.60
    ibr
    0.59
    cliffe
    0.58
    ãĤ¦ãĤ¹
    0.58
     Osw
    0.57
    issan
    0.57
    Activations Density 10.365%

    No Known Activations