© 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. 8-RES-JB
    11. 22564
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, including states, cities, and universities

    oai_token-act-pair · gpt-3.5-turbo

    expressions of inability or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suspic
    -0.61
    agents
    -0.61
    ©¶æ
    -0.60
    agent
    -0.59
     Gujar
    -0.55
     Pakistani
    -0.54
    mans
    -0.53
    hid
    -0.51
     ISI
    -0.51
    utsu
    -0.51
    POSITIVE LOGITS
     rebuilt
    0.71
     rebuilding
    0.63
    oother
    0.63
     rebuild
    0.60
     Congratulations
    0.59
     goodbye
    0.58
     Horizons
    0.58
    bye
    0.57
     postponed
    0.55
     Tomorrow
    0.55
    Activations Density 2.418%

    No Known Activations