© 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. 8698
    Prev
    Next
    INDEX
    Explanations

    words related to negative social perceptions or attitudes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to stigma and its effects

    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
    apeake
    -0.83
    ropolitan
    -0.81
    tes
    -0.81
    audi
    -0.75
    rams
    -0.71
    rote
    -0.70
    ebus
    -0.69
    gran
    -0.68
     Eucl
    -0.68
    hire
    -0.68
    POSITIVE LOGITS
     stigma
    1.31
     stigmat
    0.94
    ikuman
    0.77
    imaru
    0.73
    ega
    0.72
    ovan
    0.71
     prejudice
    0.70
     ostr
    0.69
     ridicule
    0.69
     attaches
    0.68
    Activations Density 0.013%

    No Known Activations