© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 18633
    Prev
    Next
    INDEX
    Explanations

    questions or statements about decision-making and evaluation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the validity or appropriateness of actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çīĪ
    -0.80
    details
    -0.75
    mares
    -0.74
    cember
    -0.72
    ãĥ©ãĥ³
    -0.70
     stares
    -0.68
    ciating
    -0.68
    moil
    -0.67
    few
    -0.66
    letal
    -0.65
    POSITIVE LOGITS
     worthwhile
    1.54
     feasible
    1.38
     acceptable
    1.34
     warranted
    1.32
     worth
    1.30
     appropriate
    1.28
     adequate
    1.28
     necessary
    1.28
     meaningful
    1.25
     accurate
    1.25
    Activations Density 0.229%

    No Known Activations