© 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. 4076
    Prev
    Next
    INDEX
    Explanations

    the phrases indicating uncertainty or doubt in a statement

    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
    +0.21
    1.0%
    354
    +0.10
    0.5%
    426
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    293
    +0.21
    0.12
    354
    +0.10
    0.11
    697
    +0.10
    0.08
    Negative Logits
    emetery
    -0.81
    ersed
    -0.69
     Penguin
    -0.67
     Passage
    -0.67
    ellar
    -0.65
     arsen
    -0.63
     Ukrain
    -0.61
     shipment
    -0.61
    ailability
    -0.60
    VERTISEMENT
    -0.59
    POSITIVE LOGITS
     necessarily
    0.91
    intend
    0.88
     myself
    0.87
     wish
    0.87
     hesitate
    0.85
     bother
    0.84
     regret
    0.82
    cha
    0.81
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.81
    Í
    0.79
    Activations Density 9.059%

    No Known Activations