© 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. 3-RES-JB
    6. 11438
    Prev
    Next
    INDEX
    Explanations

    keywords related to significant events or developments

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate future predictions or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vaugh
    -0.60
    ãĤ´ãĥ³
    -0.57
    ãĤĮ
    -0.54
    ãĥ¼ãĥĨ
    -0.52
    ]+
    -0.50
    ãĥĩãĤ£
    -0.50
    ãĥ¼ãĥ³
    -0.49
     thous
    -0.49
     predec
    -0.49
    chuk
    -0.49
    POSITIVE LOGITS
     largeDownload
    0.60
    taboola
    0.56
     sharply
    0.51
    UTERS
    0.50
    pin
    0.49
    zbollah
    0.49
     REUTERS
    0.48
    othes
    0.47
    conduct
    0.46
    reach
    0.46
    Activations Density 3.041%

    No Known Activations