© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 3602
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of individuals with honorific titles

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of a specific individual referred to as "Mr. 2"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eleph
    -0.88
     exting
    -0.86
     pione
    -0.79
     tremend
    -0.75
    Þ
    -0.74
    ©¶æ
    -0.73
     practition
    -0.70
    aditional
    -0.69
     oun
    -0.68
    »Ĵ
    -0.68
    POSITIVE LOGITS
    .,
    1.04
    .
    0.96
    .;
    0.93
    .,"
    0.92
    ./
    0.92
    .),
    0.88
    .—
    0.87
    ._
    0.85
    .-
    0.84
    .?
    0.82
    Activations Density 0.023%

    No Known Activations