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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-RES-JB
    6. 21065
    Prev
    Next
    INDEX
    Explanations

    rare characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of empty or whitespace characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raints
    -0.89
     disadvant
    -0.89
     manif
    -0.87
    schild
    -0.84
    pheus
    -0.79
     mathemat
    -0.78
    awaru
    -0.75
     subord
    -0.74
     vulner
    -0.73
     Instr
    -0.72
    POSITIVE LOGITS
    ħ
    0.94
     ILCS
    0.90
    ı
    0.89
    VERTISEMENT
    0.84
    ®
    0.84
    Ķ
    0.83
    æľ
    0.83
    ļ
    0.83
    STAR
    0.82
     âĢº
    0.81
    Activations Density 0.034%

    No Known Activations