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. 7-RES-JB
    6. 24454
    Prev
    Next
    INDEX
    Explanations

    technology-related terms, economic concepts, and geopolitical locations

    oai_token-act-pair · gpt-3.5-turbo

    common conjunctions and phrases that contribute to complex sentence structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ograp
    -0.75
    zing
    -0.73
    mx
    -0.71
    xe
    -0.70
    ienne
    -0.69
    endo
    -0.69
    xb
    -0.69
    clip
    -0.69
    emaker
    -0.68
    rio
    -0.67
    POSITIVE LOGITS
     respectively
    2.27
     alike
    1.33
    depending
    1.24
     depending
    1.06
     whichever
    0.96
     moreover
    0.96
     etc
    0.96
     totaling
    0.82
     plus
    0.82
    etc
    0.81
    Activations Density 0.372%

    No Known Activations