© 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. 7767
    Prev
    Next
    INDEX
    Explanations

    terms related to civic involvements or activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to civic responsibility and engagement

    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
    xual
    -0.81
    ldon
    -0.78
    uca
    -0.69
    essee
    -0.68
    erer
    -0.67
    ractive
    -0.67
    ered
    -0.67
    stab
    -0.66
     Centauri
    -0.66
    kers
    -0.65
    POSITIVE LOGITS
    ãĤ©
    0.82
     Participation
    0.77
     Auditor
    0.75
     engagement
    0.74
    izational
    0.74
    entric
    0.69
     renewal
    0.68
    iew
    0.67
     minded
    0.67
     participation
    0.67
    Activations Density 0.033%

    No Known Activations