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. 12-RES-JB
    6. 14587
    Prev
    Next
    INDEX
    Explanations

    technical issues related to hardware or software

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    technical issues and troubleshooting related to computer and device operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     articulated
    -0.76
    knit
    -0.75
     Breed
    -0.74
     Collective
    -0.71
     Zup
    -0.69
     Shap
    -0.67
     Coh
    -0.66
     Columb
    -0.63
     syll
    -0.62
     finalists
    -0.62
    POSITIVE LOGITS
     timeout
    1.12
     uninstall
    1.08
     reboot
    0.99
     error
    0.99
     crashes
    0.98
     lockout
    0.97
     restart
    0.97
     permissions
    0.96
    Timeout
    0.95
     outage
    0.95
    Activations Density 0.357%

    No Known Activations