© 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. 9-RES-JB
    11. 1710
    Prev
    Next
    INDEX
    Explanations

    the phrase "best known for."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "best known for" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.76
    akings
    -0.73
    plet
    -0.65
    pering
    -0.63
    athi
    -0.62
    wake
    -0.61
    ework
    -0.61
    ueller
    -0.60
    render
    -0.60
    akedown
    -0.60
    POSITIVE LOGITS
     anecd
    0.89
     internationally
    0.86
     for
    0.81
     fond
    0.80
     chiefly
    0.75
     worldwide
    0.74
     globally
    0.72
     locally
    0.71
    arily
    0.69
     principally
    0.68
    Activations Density 0.073%

    No Known Activations