© 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. 11-RES-JB
    6. 7145
    Prev
    Next
    INDEX
    Explanations

    HTML tags related to product information or descriptions

    oai_token-act-pair · gpt-3.5-turbo
    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
    etheless
    -0.92
     exha
    -0.82
     veter
    -0.80
     peac
    -0.80
     unification
    -0.80
     ende
    -0.77
    atical
    -0.76
     territ
    -0.73
     undermin
    -0.70
     symp
    -0.70
    POSITIVE LOGITS
     </
    1.42
     <!--
    1.36
     <
    1.31
    {{
    1.20
    )</
    1.13
     {{
    1.11
    .</
    1.08
    Hello
    1.07
    ${
    1.06
    âĸij
    1.02
    Activations Density 0.035%

    No Known Activations