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. 8-RES-JB
    6. 22007
    Prev
    Next
    INDEX
    Explanations

    requests for feedback or comments

    oai_token-act-pair · gpt-3.5-turbo

    requests for user feedback and comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ccording
    -0.61
    NV
    -0.60
     malls
    -0.60
     fatigue
    -0.60
     Recession
    -0.59
     gunned
    -0.58
     Paddock
    -0.58
    ¥µ
    -0.57
     Bauer
    -0.57
     deferred
    -0.56
    POSITIVE LOGITS
     :)
    0.87
     URL
    0.84
     thanking
    0.84
     preferably
    0.83
     initials
    0.82
     answ
    0.82
     ;)
    0.82
    vertisement
    0.82
     recipient
    0.80
    gmail
    0.79
    Activations Density 0.511%

    No Known Activations