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

    Neuronpedia

    APICircuit 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. 8-RES-JB
    6. 16585
    Prev
    Next
    INDEX
    Explanations

    technical information related to data and document formatting

    oai_token-act-pair · gpt-3.5-turbo

    content related to downloadable or data-related features

    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
    irs
    -0.78
    aun
    -0.74
    gradation
    -0.70
    oux
    -0.69
    aign
    -0.68
     satellites
    -0.68
    ija
    -0.67
    pas
    -0.65
    uay
    -0.65
    eday
    -0.64
    POSITIVE LOGITS
    rawdownloadcloneembedreportprint
    0.85
     Paste
    0.82
     "$:/
    0.79
    Written
    0.73
    Contents
    0.72
     Written
    0.69
     Contents
    0.69
    ©¶æ¥µ
    0.68
    ----------------------------------------------------------------
    0.68
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.67
    Activations Density 0.039%

    No Known Activations