© 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. 1-RES-JB
    11. 20061
    Prev
    Next
    INDEX
    Explanations

    references to the British rock band "The Who"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Who."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MER
    -0.89
    rations
    -0.77
    interstitial
    -0.69
    outer
    -0.69
    âĶģ
    -0.65
    pit
    -0.63
    à¥
    -0.62
    ANA
    -0.61
    UT
    -0.61
    çĶ°
    -0.61
    POSITIVE LOGITS
    soever
    1.63
    abouts
    0.94
    tymology
    0.88
     trave
    0.87
     else
    0.82
    govtrack
    0.81
    resy
    0.80
    ileaks
    0.78
    eday
    0.78
    ortium
    0.78
    Activations Density 0.044%

    No Known Activations