© 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. 7-RES-JB
    11. 23413
    Prev
    Next
    INDEX
    Explanations

    questions or statements involving the phrase "in the first place."

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "in the first place."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cest
    -0.68
    raltar
    -0.68
    dr
    -0.65
    inal
    -0.65
    iami
    -0.62
    mens
    -0.61
     Doors
    -0.61
     Ranch
    -0.60
    STD
    -0.59
     Barney
    -0.59
    POSITIVE LOGITS
    ãĢĤ
    0.73
    ¶
    0.71
    DonaldTrump
    0.67
     whatsoever
    0.66
    .
    0.65
    lihood
    0.65
    .,
    0.65
    !.
    0.64
    !
    0.64
    forth
    0.64
    Activations Density 0.020%

    No Known Activations