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. 8337
    Prev
    Next
    INDEX
    Explanations

    time-related information structured in a specific way

    oai_token-act-pair · gpt-3.5-turbo

    patterns related to political references or identifiers

    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
    xual
    -0.69
     breathing
    -0.66
     hereditary
    -0.65
     Diesel
    -0.65
     Squadron
    -0.64
     descendants
    -0.64
     Insect
    -0.63
     Utility
    -0.63
     inheritance
    -0.63
     enriched
    -0.63
    POSITIVE LOGITS
    noon
    1.13
     01
    1.00
     02
    0.99
     09
    0.97
     03
    0.96
    November
    0.96
    onday
    0.96
    January
    0.96
     08
    0.95
     07
    0.94
    Activations Density 0.089%

    No Known Activations