© 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. 9499
    Prev
    Next
    INDEX
    Explanations

    specific details or actions that stand out within a larger context

    oai_token-act-pair · gpt-3.5-turbo

    the word "specifically" and its variants, indicating a focus on detailed explanations or clarifications

    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
    assic
    -0.77
    76561
    -0.77
    Sil
    -0.70
    OPA
    -0.69
    unts
    -0.69
    ãĤ§
    -0.66
    çĽ
    -0.64
     Stockholm
    -0.63
    ozo
    -0.62
     li
    -0.61
    POSITIVE LOGITS
    abulary
    0.89
     Specifically
    0.87
    eous
    0.80
    wcs
    0.80
    htaking
    0.80
    insula
    0.79
    Specifically
    0.79
    graded
    0.79
    æ©Ł
    0.79
    rontal
    0.79
    Activations Density 0.011%

    No Known Activations