© 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. 40436
    Prev
    Next
    INDEX
    Explanations

    names or references related to the name "Carl."

    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
    288
    +0.15
    0.7%
    447
    +0.15
    0.7%
    549
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.19
    326
    +0.15
    0.18
    68
    +0.14
    0.06
    Negative Logits
     nomine
    -0.74
    PDATE
    -0.73
    HER
    -0.71
    lda
    -0.69
     scant
    -0.68
    LOAD
    -0.66
    lled
    -0.66
    FY
    -0.65
     disposed
    -0.63
     gearing
    -0.63
    POSITIVE LOGITS
    isle
    1.67
    obal
    1.11
    otta
    1.02
    ota
    1.02
    osaurus
    0.99
    izabeth
    0.98
     XVI
    0.95
     Jung
    0.93
    azar
    0.93
    stadt
    0.92
    Activations Density 5.380%

    No Known Activations