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. 10-RES-JB
    6. 14851
    Prev
    Next
    INDEX
    Explanations

    opinions or conclusions expressed with strong certainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conjecture or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prus
    -0.66
    ierrez
    -0.66
    ptives
    -0.65
    regor
    -0.64
    uez
    -0.63
    iasco
    -0.62
    uese
    -0.61
    psons
    -0.61
    alez
    -0.61
    vez
    -0.60
    POSITIVE LOGITS
    .
    1.13
    ;
    1.02
    .-
    1.01
     ;)
    0.98
     :-)
    0.98
    .[
    0.94
    .)
    0.94
    .;
    0.93
     :)
    0.93
    !
    0.93
    Activations Density 0.284%

    No Known Activations