© 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. 7-RES-JB
    11. 13527
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific geographic location, potentially related to conflict or political figures

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific name or term related to individuals or entities in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lishing
    -0.84
    ertodd
    -0.78
    lier
    -0.78
    ridges
    -0.78
    itud
    -0.77
    ãĥ¼ãĥ«
    -0.76
    theless
    -0.75
    TON
    -0.74
    fully
    -0.74
    ting
    -0.71
    POSITIVE LOGITS
    Äĩ
    1.10
    ya
    0.88
    emi
    0.80
    ye
    0.80
    ennes
    0.80
    plom
    0.79
    yah
    0.75
    alez
    0.72
    oun
    0.72
    arbon
    0.72
    Activations Density 0.029%

    No Known Activations