Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 1684
    Prev
    Next
    INDEX
    Explanations

    text sequences containing special characters followed by numbers

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a specific character or symbol

    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
     decomp
    -0.82
     interf
    -0.79
     mathemat
    -0.75
     fortun
    -0.71
    Downloadha
    -0.71
     Palest
    -0.68
     horizont
    -0.68
     photoc
    -0.67
     transc
    -0.66
     Osw
    -0.66
    POSITIVE LOGITS
    ¬
    1.45
    Ļ
    1.36
    £
    1.24
    ª
    1.23
    į
    1.21
    ĸ
    1.21
    Ī
    1.21
    ı
    1.20
    ĵ
    1.20
    ħ
    1.19
    Activations Density 0.382%

    No Known Activations