© 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. 6-RES-JB
    11. 17459
    Prev
    Next
    INDEX
    Explanations

    words related to government, organizations, and policy enforcement

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and breaks in text, particularly commas and the end of text marker

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oshenko
    -0.81
    icol
    -0.80
    ighters
    -0.73
    nings
    -0.68
     sidx
    -0.66
    fal
    -0.66
    ragon
    -0.65
    姫
    -0.64
     slider
    -0.64
    lem
    -0.63
    POSITIVE LOGITS
     academia
    0.77
    £ı
    0.73
     Disclosure
    0.72
     overseen
    0.72
     DHS
    0.71
     Applicant
    0.69
     oversight
    0.69
     FOIA
    0.69
     Colleges
    0.68
     Watergate
    0.67
    Activations Density 1.043%

    No Known Activations