© 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. 1-RES-JB
    11. 16843
    Prev
    Next
    INDEX
    Explanations

    geographical locations or entities

    oai_token-act-pair · gpt-3.5-turbo

    the term "gent" related to social or diplomatic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WT
    -0.77
    ADE
    -0.75
    IRO
    -0.71
    oufl
    -0.71
    esty
    -0.68
    ecause
    -0.68
    senal
    -0.68
    Downloadha
    -0.66
    qqa
    -0.65
    inki
    -0.65
    POSITIVE LOGITS
    gent
    1.49
    lus
    0.80
    rant
    0.75
    rants
    0.75
    ente
    0.74
    nesses
    0.72
    gently
    0.71
    rification
    0.70
    é¾įå¥ij士
    0.70
    wick
    0.69
    Activations Density 0.006%

    No Known Activations