© 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. 10-RES-JB
    11. 2647
    Prev
    Next
    INDEX
    Explanations

    facts and results from reports or studies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to election results and statistics

    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
    emis
    -0.86
     Quit
    -0.79
    lication
    -0.74
     Span
    -0.68
    iless
    -0.65
    sylvania
    -0.65
     Flavoring
    -0.64
     respons
    -0.62
     pract
    -0.62
    Activ
    -0.62
    POSITIVE LOGITS
     skewed
    1.27
     accurate
    1.00
     inflated
    0.99
     tallied
    0.96
     discrep
    0.95
     predictive
    0.90
     snapshots
    0.89
     discrepancies
    0.89
     anomalies
    0.89
     graphs
    0.88
    Activations Density 0.258%

    No Known Activations