© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 34915
    Prev
    Next
    INDEX
    Explanations

    characters or phrases that express urgency or intensity

    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
    373
    +0.15
    0.9%
    671
    +0.08
    0.5%
    418
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.21
    422
    +0.08
    0.11
    616
    +0.08
    0.10
    Negative Logits
    tein
    -0.50
    terday
    -0.49
    omething
    -0.48
    isin
    -0.47
     Aires
    -0.46
    paio
    -0.46
    ometimes
    -0.46
    nesday
    -0.46
    Ô
    -0.46
    Cola
    -0.45
    POSITIVE LOGITS
    liest
    0.86
    iest
    0.81
    osphere
    0.72
    waters
    0.67
    elight
    0.65
    est
    0.62
    forts
    0.62
    most
    0.58
    runners
    0.58
    env
    0.57
    Activations Density 4.828%

    No Known Activations