© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 10058
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Sa" followed by characters, likely signaling a specific entity or name

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Sa" or similar prefixes in various contexts, likely related to a specific individual or entity associated with those terms

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

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.86
    tics
    -0.82
    papers
    -0.82
    mercial
    -0.76
     Turing
    -0.74
    payer
    -0.73
    theless
    -0.72
    breaks
    -0.68
    etheless
    -0.67
    tyard
    -0.66
    POSITIVE LOGITS
    igon
    1.00
    uth
    0.97
    iva
    0.95
    adish
    0.94
    uten
    0.94
    pling
    0.94
    eed
    0.89
    vers
    0.88
    Sa
    0.88
     Sa
    0.87
    Activations Density 0.006%

    No Known Activations