Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45081
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a short amount of time

    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
    0.7%
    302
    +0.11
    0.5%
    231
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    330
    +0.15
    0.08
    726
    +0.11
    0.08
    195
    +0.11
    0.00
    Negative Logits
    ceans
    -0.74
    âĹ¼
    -0.64
    Train
    -0.64
    rogens
    -0.63
    JV
    -0.62
     Polo
    -0.61
    IVER
    -0.61
    Training
    -0.61
    SEA
    -0.60
    çͰ
    -0.60
    POSITIVE LOGITS
    cases
    1.26
    case
    1.17
    erate
    0.86
     stint
    0.84
     glimps
    0.82
    itud
    0.78
    ebin
    0.76
     periods
    0.73
    aneously
    0.73
    ener
    0.71
    Activations Density 6.042%

    No Known Activations