© 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. 8-RES-JB
    11. 7586
    Prev
    Next
    INDEX
    Explanations

    hyperlinks and URLs

    oai_token-act-pair · gpt-3.5-turbo

    URLs or links within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RECT
    -0.73
     Ending
    -0.72
     Ruth
    -0.70
     Relief
    -0.70
     Niger
    -0.68
     Cham
    -0.68
    ï¸ı
    -0.67
     Excellence
    -0.67
    ĺħ
    -0.67
     Hazel
    -0.65
    POSITIVE LOGITS
    imgur
    0.96
    agnar
    0.93
    ebin
    0.93
    cdn
    0.92
    bnb
    0.91
    upload
    0.90
    online
    0.89
    wiki
    0.85
    blogs
    0.85
     github
    0.85
    Activations Density 0.029%

    No Known Activations