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. 8679
    Prev
    Next
    INDEX
    Explanations

    conclusions or inferences drawn from information or data

    oai_token-act-pair · gpt-3.5-turbo
    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
    skill
    -0.68
    thumbnails
    -0.67
    lighting
    -0.64
    ophon
    -0.64
    ansk
    -0.61
    Interstitial
    -0.61
     havoc
    -0.59
    artney
    -0.59
     contrace
    -0.58
    amen
    -0.58
    POSITIVE LOGITS
     conclusions
    1.13
     regarding
    0.99
     extrap
    0.98
     conclusion
    0.95
    abl
    0.93
     conjecture
    0.89
     drawn
    0.89
     glean
    0.88
     about
    0.87
     inferred
    0.86
    Activations Density 0.088%

    No Known Activations