Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 7834
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a comparison or contrast in terms of changes or potential consequences under a specific condition or leadership

    oai_token-act-pair · gpt-3.5-turbo

    references to a state of being or conditions that are "under" a certain situation or rule

    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
    ument
    -0.72
    ãĥĩãĤ£
    -0.64
    aturday
    -0.63
    veland
    -0.63
    ern
    -0.63
     ashore
    -0.62
    ospace
    -0.60
    chini
    -0.59
    Inside
    -0.59
    `
    -0.58
    POSITIVE LOGITS
    pins
    1.16
    cuts
    1.09
    lines
    1.08
    lining
    1.06
    performing
    1.05
    cutting
    1.01
    neath
    1.01
    lying
    1.00
    dogs
    0.99
    represented
    0.95
    Activations Density 0.053%

    No Known Activations