© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 17203
    Prev
    Next
    INDEX
    Explanations

    words related to clues or hints

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "clue" and its variants, indicating a focus on hints or pieces of information related to mysteries or investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rior
    -0.76
    requency
    -0.69
    kus
    -0.69
    imposed
    -0.68
    die
    -0.68
    rifice
    -0.66
     martyr
    -0.66
    awk
    -0.65
    awar
    -0.64
    oÄŁ
    -0.64
    POSITIVE LOGITS
     clue
    1.19
     hint
    1.10
     clues
    1.09
     hints
    0.89
    wcs
    0.83
     glean
    0.79
    DragonMagazine
    0.73
     vault
    0.73
    hig
    0.71
    TextColor
    0.70
    Activations Density 0.010%

    No Known Activations