© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 13101
    Prev
    Next
    INDEX
    Explanations

    mentions of violence or conflict

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, particularly periods and commas

    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
     affordability
    -0.89
     volunte
    -0.87
     veter
    -0.84
     corrid
    -0.83
     affili
    -0.83
     microbiome
    -0.81
     pse
    -0.80
     nodd
    -0.79
     dips
    -0.78
     consistency
    -0.76
    POSITIVE LOGITS
     Afterwards
    1.81
     Eventually
    1.74
     Shortly
    1.70
     However
    1.69
     Later
    1.67
     Whilst
    1.66
     Upon
    1.65
     Fortunately
    1.59
     Despite
    1.55
     Meanwhile
    1.55
    Activations Density 0.195%

    No Known Activations