© 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. 6-RES-JB
    11. 19805
    Prev
    Next
    INDEX
    Explanations

    sequences of alphanumeric characters

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numbers and letters that may represent device identifiers or codes

    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
    DonaldTrump
    -0.90
    Ü
    -0.82
     mathemat
    -0.66
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.64
     urgently
    -0.63
     tractor
    -0.62
    itialized
    -0.62
     bisc
    -0.62
     weekday
    -0.62
     billionaires
    -0.61
    POSITIVE LOGITS
    fy
    0.87
     attRot
    0.85
    )))
    0.73
    }\
    0.71
    phrine
    0.70
    etc
    0.70
     etc
    0.68
    \">
    0.68
    eson
    0.66
    dd
    0.66
    Activations Density 0.053%

    No Known Activations