© 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. 20149
    Prev
    Next
    INDEX
    Explanations

    terms related to physical construction and immersion in a setting

    oai_token-act-pair · gpt-3.5-turbo

    elements related to significant events or milestones

    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
     ..."
    -0.67
    .'"
    -0.60
    ";
    -0.59
     [...]
    -0.57
    !'"
    -0.56
     âĢ¦"
    -0.53
     ."
    -0.52
     [âĢ¦]
    -0.52
    '."
    -0.51
    ..."
    -0.51
    POSITIVE LOGITS
    ewitness
    0.70
    answered
    0.68
    autions
    0.67
    OVER
    0.60
    ãĥĦ
    0.60
    Browser
    0.59
    ori
    0.57
    cknowled
    0.57
    ELY
    0.57
    atform
    0.56
    Activations Density 2.632%

    No Known Activations