© 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. 2-RES-JB
    11. 9267
    Prev
    Next
    INDEX
    Explanations

    metadata about posts such as authors and timestamps

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "posted by."

    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
    bia
    -0.79
    inea
    -0.78
    ndum
    -0.78
    hement
    -0.77
    atem
    -0.75
    inary
    -0.72
    asy
    -0.71
    qqa
    -0.71
    imately
    -0.68
    rosse
    -0.67
    POSITIVE LOGITS
     virtue
    1.04
    product
    0.82
    laws
    0.81
    products
    0.80
     STATS
    0.79
     selecting
    0.77
     adding
    0.73
     clicking
    0.71
    akuya
    0.68
     inserting
    0.66
    Activations Density 0.238%

    No Known Activations