© 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. 6257
    Prev
    Next
    INDEX
    Explanations

    specific patterns of characters related to dates and information labels

    oai_token-act-pair · gpt-3.5-turbo

    elements related to movie release years and associated information

    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
    ãĤ§
    -0.88
    ãĥ¥
    -0.75
    oat
    -0.66
    ement
    -0.65
    sten
    -0.64
    ãĤ©
    -0.64
    air
    -0.63
    ccording
    -0.63
    cyclopedia
    -0.63
    ãĤ¢ãĥ«
    -0.62
    POSITIVE LOGITS
     Lastly
    0.72
     }}
    0.70
     --------------------
    0.70
     Syndicate
    0.69
     Incarn
    0.69
    ];
    0.69
     };
    0.69
     Finally
    0.66
     =================================================================
    0.66
     UCHIJ
    0.64
    Activations Density 0.126%

    No Known Activations