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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20470
    Prev
    Next
    INDEX
    Explanations

    negative evaluations or criticisms

    oai_token-act-pair · gpt-3.5-turbo

    negations or expressions of dissatisfaction

    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
    cens
    -0.71
    moil
    -0.69
    tein
    -0.68
     Mayhem
    -0.68
     weap
    -0.67
     sqor
    -0.65
    emonium
    -0.65
    ãĥ©ãĥ³
    -0.65
    udicrous
    -0.62
     folly
    -0.62
    POSITIVE LOGITS
     adequately
    1.11
     sufficiently
    1.09
     adequate
    1.00
     enough
    1.00
     suited
    0.96
     conducive
    0.94
     sufficient
    0.92
    enough
    0.91
     fit
    0.88
     properly
    0.87
    Activations Density 0.276%

    No Known Activations