© 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. 3127
    Prev
    Next
    INDEX
    Explanations

    technology related terms related to image toggling

    oai_token-act-pair · gpt-3.5-turbo

    segments related to image toggling or display actions

    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
    esses
    -0.76
    ivism
    -0.64
     Expend
    -0.63
    comed
    -0.62
    eday
    -0.62
    bats
    -0.62
    nov
    -0.61
    metic
    -0.60
     Integrity
    -0.60
    naires
    -0.60
    POSITIVE LOGITS
     caption
    1.11
     toggle
    0.92
    ãĤ´
    0.79
     Courtesy
    0.78
     "$:/
    0.78
    ãĥ¼ãĤ¯
    0.74
    è£ħ
    0.74
    ption
    0.73
    gha
    0.72
    ãĤ¤
    0.71
    Activations Density 0.003%

    No Known Activations