© 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. 10-RES-JB
    11. 16424
    Prev
    Next
    INDEX
    Explanations

    informative points or tips related to various topics

    oai_token-act-pair · gpt-3.5-turbo

    inquiries about methods or ideas for enhancing efficiency and productivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fucked
    -0.75
    aign
    -0.74
     equival
    -0.72
    iannopoulos
    -0.72
     retard
    -0.68
     equivalent
    -0.66
     externalToEVAOnly
    -0.66
     retarded
    -0.66
    acan
    -0.65
    emort
    -0.65
    POSITIVE LOGITS
    Below
    1.14
     Below
    1.12
     Luckily
    1.01
    Whether
    1.01
     Browse
    1.00
     Explore
    1.00
     Understanding
    0.96
     Fortunately
    0.95
    Luckily
    0.93
    Fortunately
    0.92
    Activations Density 0.485%

    No Known Activations