© 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. 4-RES-JB
    11. 19443
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict and controversy

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to social justice and advocacy issues

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

    No Comments

    Negative Logits
     Canaver
    -0.73
    ften
    -0.66
    utra
    -0.65
     THERE
    -0.65
    apist
    -0.64
    IVER
    -0.63
    ittee
    -0.62
    rette
    -0.62
     largeDownload
    -0.61
    ottest
    -0.61
    POSITIVE LOGITS
     situations
    0.82
     levels
    0.81
     objects
    0.76
     periods
    0.76
     engagements
    0.76
     intermedi
    0.75
     backgrounds
    0.75
     areas
    0.74
     materials
    0.74
     foreign
    0.74
    Activations Density 0.710%

    No Known Activations