Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 20362
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Sym" followed by a number, potentially in the context of symposiums

    oai_token-act-pair · gpt-3.5-turbo

    references to symposiums and related events

    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
    patrick
    -0.83
    erness
    -0.76
    holding
    -0.67
    WARD
    -0.66
     Palmer
    -0.65
    aways
    -0.64
    pour
    -0.64
    mallow
    -0.64
    iage
    -0.63
    dit
    -0.63
    POSITIVE LOGITS
    posium
    1.66
    phony
    1.23
    ptoms
    1.17
    pt
    0.82
     Sym
    0.80
    chron
    0.79
    ph
    0.78
    pta
    0.78
    onic
    0.77
    abeth
    0.77
    Activations Density 0.054%

    No Known Activations