Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 4631
    Prev
    Next
    INDEX
    Explanations

    information about organizational structure, including the number of members and employees

    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
     remedies
    -0.66
    artifacts
    -0.65
     pitfalls
    -0.64
    uberty
    -0.63
     ruin
    -0.62
     Trick
    -0.60
     disaster
    -0.60
     corrective
    -0.60
     frustration
    -0.60
     spoil
    -0.59
    POSITIVE LOGITS
     active
    1.10
     headquartered
    1.09
     registered
    1.07
     enrolled
    1.05
     stationed
    1.04
     worldwide
    1.02
     numbering
    1.02
     residing
    0.99
     operating
    0.96
     living
    0.96
    Activations Density 0.410%

    No Known Activations