© 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. 0-RES-JB
    6. 22326
    Prev
    Next
    INDEX
    Explanations

    strings or acronyms related to technology products or files

    oai_token-act-pair · gpt-3.5-turbo

    acronyms and specific terms related to technologies or formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hilbert
    -0.73
    NetMessage
    -0.72
     Crow
    -0.70
    pling
    -0.68
     mas
    -0.68
     grou
    -0.67
     Walters
    -0.67
     mull
    -0.66
     haunted
    -0.65
     Riverside
    -0.64
    POSITIVE LOGITS
    XT
    4.12
     XT
    1.95
    txt
    1.37
     NXT
    1.28
    iture
    1.27
    LT
    1.17
    XL
    1.14
    EXT
    1.08
     LT
    1.04
     Unt
    1.04
    Activations Density 0.064%

    No Known Activations