© 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. 7-RES-JB
    11. 18708
    Prev
    Next
    INDEX
    Explanations

    specific references to historical dates

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to historical timelines or origins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.88
    ellow
    -0.86
    ĺħ
    -0.74
    achy
    -0.73
    heit
    -0.71
    ļéĨĴ
    -0.69
    paio
    -0.66
    benefit
    -0.66
    ison
    -0.65
    ictive
    -0.65
    POSITIVE LOGITS
     1979
    1.00
     1952
    0.96
     1948
    0.96
     1982
    0.96
     1978
    0.95
     1976
    0.95
     infancy
    0.94
     1954
    0.93
     1960
    0.93
     1950
    0.93
    Activations Density 0.099%

    No Known Activations