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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 17663
    Prev
    Next
    INDEX
    Explanations

    names with special characters, possibly in the context of addresses or organizations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences 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 @ 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
     Palestin
    -0.66
     precaution
    -0.62
     reproduction
    -0.62
     maximum
    -0.62
     Malta
    -0.62
     jog
    -0.62
     sacrific
    -0.62
     paperback
    -0.61
     recomb
    -0.61
     vulner
    -0.60
    POSITIVE LOGITS
    ï¸
    0.98
    iversary
    0.93
    ï¸ı
    0.93
    tre
    0.90
    alone
    0.83
    lime
    0.82
    creator
    0.82
    own
    0.81
    worthiness
    0.81
    REDACTED
    0.81
    Activations Density 0.295%

    No Known Activations