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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 11-RES-JB
    6. 20108
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    empty or non-informative sections in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pressures
    -0.70
     growing
    -0.70
     conferences
    -0.70
     panels
    -0.68
     spreads
    -0.68
     drawing
    -0.68
     execution
    -0.66
     segments
    -0.66
     cameras
    -0.64
     assignments
    -0.64
    POSITIVE LOGITS
    ãĥ³ãĤ¸
    1.24
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.22
    à¨
    1.19
    ãĥ¼ãĥ«
    1.15
    âĸ¬âĸ¬
    1.12
    ãĥĥãĥĪ
    1.12
    ãĥĥãĤ¯
    1.10
    à©
    1.09
    ãĥ¼ãĥ
    1.09
    ãĥĺ
    1.08
    Activations Density 0.029%

    No Known Activations