© 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. 2-RES-JB
    11. 9256
    Prev
    Next
    INDEX
    Explanations

    references to legal codes

    oai_token-act-pair · gpt-3.5-turbo

    references to legal codes and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    swer
    -0.76
     Ples
    -0.71
    ishly
    -0.70
    esville
    -0.70
    iatus
    -0.68
    strous
    -0.67
    igation
    -0.67
     Fantastic
    -0.65
     Ves
    -0.64
     Flavoring
    -0.63
    POSITIVE LOGITS
     codes
    1.06
    codes
    0.98
     code
    0.97
    otle
    0.94
    code
    0.93
     snippet
    0.92
     Codes
    0.89
     Code
    0.88
    Code
    0.86
     CODE
    0.76
    Activations Density 0.013%

    No Known Activations