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. 16051
    Prev
    Next
    INDEX
    Explanations

    statements showing seriousness, concern, or action towards specific issues or incidents

    oai_token-act-pair · gpt-3.5-turbo

    terms related to serious concerns or allegations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ificent
    -0.64
     Smile
    -0.64
     Retrieved
    -0.62
     Machina
    -0.60
    regate
    -0.58
    etheless
    -0.58
    alde
    -0.57
    otten
    -0.57
     Stretch
    -0.56
     wonders
    -0.54
    POSITIVE LOGITS
     seriously
    1.54
     Seriously
    1.26
     aback
    1.06
     hostage
    1.06
     lightly
    0.98
     offline
    0.88
     into
    0.87
     stride
    0.84
     literally
    0.84
     VERY
    0.83
    Activations Density 0.105%

    No Known Activations