© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 6094
    Prev
    Next
    INDEX
    Explanations

    country names and organizations

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and conjunction-like elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ESE
    -0.70
    icka
    -0.65
    usercontent
    -0.65
    ruary
    -0.63
    atform
    -0.60
     Revis
    -0.57
     cruiser
    -0.57
     rewritten
    -0.57
    forth
    -0.57
     err
    -0.57
    POSITIVE LOGITS
    ãĥĨ
    0.80
    igham
    0.74
    bors
    0.70
    emies
    0.69
     buds
    0.63
    ãĥł
    0.62
    achus
    0.61
    song
    0.61
    arth
    0.61
    eping
    0.61
    Activations Density 0.411%

    No Known Activations