© 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. 10-RES-JB
    11. 17334
    Prev
    Next
    INDEX
    Explanations

    phrases related to investigation and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to issues of injustice and social problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.85
    soType
    -0.66
    pmwiki
    -0.63
     prosecut
    -0.63
     disclaimer
    -0.62
    ãĤ´ãĥ³
    -0.60
     EDIT
    -0.59
     archaeologists
    -0.58
     Editors
    -0.57
    Asset
    -0.57
    POSITIVE LOGITS
    nings
    0.65
    abies
    0.65
    )",
    0.64
    existent
    0.62
    ivities
    0.59
    '"
    0.58
    )"
    0.58
    ','
    0.57
    yip
    0.57
    violent
    0.56
    Activations Density 0.919%

    No Known Activations