© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 3015
    Prev
    Next
    INDEX
    Explanations

    numerical values within text

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and structural markers in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ©
    -0.97
    hart
    -0.94
     Sag
    -0.90
    TAG
    -0.85
    455
    -0.84
    hern
    -0.79
    »Ĵ
    -0.78
    ¥µ
    -0.74
    Stack
    -0.73
     Nost
    -0.73
    POSITIVE LOGITS
    lee
    0.92
     Rae
    0.87
    DA
    0.84
     Rai
    0.84
    ael
    0.80
    978
    0.79
    da
    0.77
    aji
    0.77
     server
    0.76
    Server
    0.75
    Activations Density 0.364%

    No Known Activations