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. 9-RES-JB
    6. 2031
    Prev
    Next
    INDEX
    Explanations

    informational phrases directing the reader to learn more about different topics or programs

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the availability of additional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffffcc
    -0.81
    mouth
    -0.74
    ãĥĨãĤ£
    -0.71
    rums
    -0.71
    usercontent
    -0.71
    istas
    -0.68
    gered
    -0.68
     Sabha
    -0.68
    albeit
    -0.67
    earth
    -0.67
    POSITIVE LOGITS
     upcoming
    0.82
     participating
    0.79
     how
    0.76
     why
    0.75
     pricing
    0.74
     your
    0.73
     our
    0.73
     volunteering
    0.70
     joining
    0.70
     developing
    0.68
    Activations Density 0.131%

    No Known Activations