© 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. 4542
    Prev
    Next
    INDEX
    Explanations

    terms related to musical jams and gatherings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "jam" in various contexts

    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
    avement
    -0.69
     Equality
    -0.64
     particulars
    -0.64
     Marketable
    -0.63
     Aires
    -0.61
     Advantage
    -0.60
     occup
    -0.59
    Claim
    -0.58
     livest
    -0.56
     Ambrose
    -0.56
    POSITIVE LOGITS
    ming
    1.43
    mer
    1.09
    mers
    1.06
    monds
    1.06
    bley
    0.98
    nit
    0.96
    pered
    0.94
    ilton
    0.93
    oon
    0.92
    antine
    0.90
    Activations Density 0.034%

    No Known Activations