© 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. 33164
    Prev
    Next
    INDEX
    Explanations

    mentions of efforts and striving in the context of various activities and goals

    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
    575
    +0.10
    0.6%
    447
    +0.10
    0.5%
    383
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.10
    0.17
    263
    +0.10
    0.08
    383
    +0.09
    0.11
    Negative Logits
    bah
    -0.59
    ockets
    -0.59
    waves
    -0.56
    picking
    -0.54
    phone
    -0.52
    Closure
    -0.51
    assault
    -0.50
    olicited
    -0.49
    rooms
    -0.49
    dor
    -0.49
    POSITIVE LOGITS
     aspire
    0.74
     striving
    0.70
     strive
    0.69
    reprene
    0.67
     aspirations
    0.65
     ambition
    0.64
    pires
    0.63
     attainment
    0.62
    rious
    0.62
    ignty
    0.62
    Activations Density 9.558%

    No Known Activations