© 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. 9-RES-JB
    11. 3597
    Prev
    Next
    INDEX
    Explanations

    mentions of percentages or numerical values

    oai_token-act-pair · gpt-3.5-turbo

    instances of a recurring symbol or character, likely associated with a particular theme

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whit
    -0.80
    nings
    -0.67
    ozy
    -0.64
     warp
    -0.64
     OB
    -0.63
     vendor
    -0.62
     brick
    -0.61
     wink
    -0.61
     Scrib
    -0.60
     itself
    -0.60
    POSITIVE LOGITS
    ¬
    1.06
    Ĵ
    1.05
    ª
    0.97
    ı
    0.96
    ¡
    0.96
    ¤
    0.94
    ¼
    0.93
    ¹
    0.93
    elong
    0.90
    Ń
    0.90
    Activations Density 0.186%

    No Known Activations