© 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. 13399
    Prev
    Next
    INDEX
    Explanations

    phrases related to government institutions or proceedings

    oai_token-act-pair · gpt-3.5-turbo

    references to Capitol Hill and related political discussions

    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
    onal
    -0.71
    rating
    -0.63
    Rating
    -0.62
    OTHER
    -0.60
    rar
    -0.59
    gins
    -0.58
    rex
    -0.58
    anan
    -0.57
    uv
    -0.57
    Title
    -0.57
    POSITIVE LOGITS
     Correspond
    0.87
    shire
    0.75
     caf
    0.74
    speech
    0.73
     desks
    0.70
     Headquarters
    0.70
     Meeting
    0.70
     headquarters
    0.70
     podium
    0.70
     offices
    0.68
    Activations Density 0.079%

    No Known Activations