© 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. 0-RES-JB
    11. 22314
    Prev
    Next
    INDEX
    Explanations

    mentions of or references to something extra or additional in content

    oai_token-act-pair · gpt-3.5-turbo

    mentions of additional features or benefits, particularly in the context of services or awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    weed
    -0.74
    ware
    -0.74
     Darius
    -0.72
    jan
    -0.70
    bryce
    -0.68
    lyn
    -0.67
     decline
    -0.66
     Bhar
    -0.65
     Becker
    -0.64
    rust
    -0.64
    POSITIVE LOGITS
     Extra
    3.51
    Extra
    3.01
    extra
    2.87
     extras
    2.27
     extra
    1.96
     Extras
    1.79
     EXT
    1.16
    EXT
    1.10
    Ext
    1.08
     Additional
    1.03
    Activations Density 0.012%

    No Known Activations