© 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. 24122
    Prev
    Next
    INDEX
    Explanations

    the title 'Mr'

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals titled "Mr" in a political context

    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
     actionGroup
    -0.81
    rawdownloadcloneembedreportprint
    -0.77
    ãĥ¼ãĥĨ
    -0.76
    ãĥ¼ãĥĨãĤ£
    -0.68
    Women
    -0.67
    ãĥ´ãĤ¡
    -0.66
    SHIP
    -0.66
    PRESS
    -0.66
    ENDED
    -0.64
     Ranked
    -0.63
    POSITIVE LOGITS
    unal
    0.84
     Mr
    0.83
    Mr
    0.78
    ertodd
    0.75
     Hussein
    0.74
    hesis
    0.71
    ufact
    0.69
    inges
    0.68
     Universe
    0.67
    cipled
    0.66
    Activations Density 0.027%

    No Known Activations