© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 12431
    Prev
    Next
    INDEX
    Explanations

    verbs related to solving or repairing something

    oai_token-act-pair · gpt-3.5-turbo

    references to solutions or repairs for problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ographies
    -0.79
    ographic
    -0.73
    ammy
    -0.68
    NetMessage
    -0.67
    ography
    -0.64
     unprotected
    -0.64
     Schwar
    -0.62
    stem
    -0.61
    utton
    -0.60
     Flavoring
    -0.59
    POSITIVE LOGITS
     fix
    0.86
    fix
    0.86
     Fix
    0.82
    FIX
    0.81
     fixing
    0.80
    esty
    0.80
    ysis
    0.77
    Fix
    0.75
    ttes
    0.73
    hift
    0.73
    Activations Density 0.010%

    No Known Activations