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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3759
    Prev
    Next
    INDEX
    Explanations

    sentences depicting dramatic or life-changing events

    oai_token-act-pair · gpt-3.5-turbo

    punctuations that signify climactic moments or endings in narratives

    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
     confir
    -0.88
     categor
    -0.85
     retention
    -0.82
    uly
    -0.77
     nodd
    -0.77
     concess
    -0.76
     minim
    -0.76
     consistency
    -0.76
     microbiome
    -0.76
     contraction
    -0.75
    POSITIVE LOGITS
     Written
    1.69
     Meanwhile
    1.54
     Along
    1.33
     Featuring
    1.29
     Unable
    1.28
     Forced
    1.28
     Suddenly
    1.24
     Eventually
    1.24
     Together
    1.24
     Luckily
    1.22
    Activations Density 0.160%

    No Known Activations