© 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. 8-RES-JB
    6. 6052
    Prev
    Next
    INDEX
    Explanations

    special characters and codes typically found in programming or technical contexts

    oai_token-act-pair · gpt-3.5-turbo

    percentage values and formatted numerical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erate
    -0.67
    oris
    -0.66
    omore
    -0.65
    olphins
    -0.61
     Tough
    -0.60
     Magnum
    -0.60
     bye
    -0.59
    Oak
    -0.59
    krit
    -0.59
     Focus
    -0.58
    POSITIVE LOGITS
    ãĤ«
    0.79
    ãĤ±
    0.78
     Azerb
    0.73
    ¯¯¯¯¯¯¯¯
    0.72
    -+
    0.71
    AAAAAAAA
    0.66
    ÙĬ
    0.66
    Ĭ
    0.66
    ß
    0.65
    TIT
    0.65
    Activations Density 0.019%

    No Known Activations