© 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. 6-RES-JB
    11. 829
    Prev
    Next
    INDEX
    Explanations

    locations or events described in news articles

    oai_token-act-pair · gpt-3.5-turbo

    sentences that lead with a period or reference a conclusion in news reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metic
    -0.69
     organis
    -0.65
    dule
    -0.63
    ures
    -0.61
     conversions
    -0.60
    igen
    -0.60
    itions
    -0.60
    ãĥ«
    -0.60
    verting
    -0.60
    bats
    -0.59
    POSITIVE LOGITS
     Speedway
    0.77
     Rece
    0.75
     Residents
    0.74
    aucuses
    0.72
     Blvd
    0.70
     Dept
    0.69
     Photographer
    0.68
     Rapids
    0.68
     Wells
    0.68
     Merrill
    0.67
    Activations Density 0.046%

    No Known Activations