© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 7605
    Prev
    Next
    INDEX
    Explanations

    references to legal or official proceedings, such as judges and rulings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "U.S." and its context in relation to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fields
    -0.70
    ebook
    -0.66
     ker
    -0.66
    adobe
    -0.65
    theless
    -0.64
    bath
    -0.63
    sticks
    -0.63
    regor
    -0.62
     Proto
    -0.60
    errors
    -0.60
    POSITIVE LOGITS
    GI
    0.99
    ESSION
    0.92
    ADA
    0.91
    IDA
    0.91
     Airways
    0.90
    .$
    0.90
    .,
    0.81
     Embassy
    0.80
     Cellular
    0.80
     Army
    0.77
    Activations Density 0.043%

    No Known Activations