© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 24305
    Prev
    Next
    INDEX
    Explanations

    proper nouns or named entities, particularly in the context of events, social programs, companies, and financial instruments

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions linking lists or multiple items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istical
    -0.76
    elle
    -0.76
    wic
    -0.74
    hemer
    -0.72
    bral
    -0.72
    ptoms
    -0.71
    amily
    -0.70
    rimination
    -0.70
    idae
    -0.70
    ãĤ¤
    -0.68
    POSITIVE LOGITS
     elsewhere
    1.18
     others
    1.13
     other
    1.04
     countless
    0.95
     assorted
    0.93
     even
    0.89
     innumerable
    0.85
     perhaps
    0.79
     possibly
    0.78
     consequently
    0.77
    Activations Density 0.210%

    No Known Activations