© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    6. 6718
    Prev
    Next
    INDEX
    Explanations

    tasks or actions related to technology or software, such as upgrading, resolving problems, drafting, installing software, processing files, or accessing information

    oai_token-act-pair · gpt-3.5-turbo

    actions or processes related to troubleshooting and system maintenance

    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
     overshadowed
    -0.53
    irk
    -0.53
     towering
    -0.53
     famed
    -0.52
     Frenchman
    -0.51
     amassed
    -0.51
     purported
    -0.51
    livious
    -0.50
     ousted
    -0.50
    ij士
    -0.49
    POSITIVE LOGITS
     Quote
    0.94
     BEFORE
    0.92
    DragonMagazine
    0.88
    ↵Âł
    0.88
     Submit
    0.86
    ¶
    0.86
     WITHOUT
    0.86
     Yourself
    0.86
     ASAP
    0.83
     </
    0.83
    Activations Density 0.567%

    No Known Activations