© 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. 7112
    Prev
    Next
    INDEX
    Explanations

    code snippets or sequences related to programming

    oai_token-act-pair · gpt-3.5-turbo
    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
    reb
    -0.77
    æĪ¦
    -0.77
    ãĥ´
    -0.74
    cro
    -0.72
    PAC
    -0.71
    çĶ°
    -0.71
    çķ
    -0.70
    Charl
    -0.70
    anship
    -0.70
    chest
    -0.70
    POSITIVE LOGITS
     =>
    1.26
     println
    1.23
     ;;
    1.18
     ¶
    1.12
     endif
    1.09
     def
    1.04
    ;;
    1.02
     assert
    1.02
     Returns
    1.01
     {:
    0.99
    Activations Density 0.115%

    No Known Activations