© 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. 10-RES-JB
    11. 9899
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals or groups with the word "Boy"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Boy" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aeda
    -1.05
    arily
    -0.77
     podium
    -0.72
     showc
    -0.71
     gallon
    -0.69
    PLA
    -0.63
    encing
    -0.63
    RIPT
    -0.61
    utations
    -0.61
    odium
    -0.61
    POSITIVE LOGITS
    friend
    1.49
    cott
    1.38
    nton
    1.38
     Scouts
    1.22
    cot
    1.20
    hood
    1.18
     Scout
    1.17
    friends
    1.13
    boy
    1.05
    stown
    1.04
    Activations Density 0.036%

    No Known Activations