© 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. 8-RES-JB
    11. 4610
    Prev
    Next
    INDEX
    Explanations

    instances of the character 'D' followed by the number 9 or 10 in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the letter "D"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bulg
    -0.76
     slurs
    -0.66
     Crusade
    -0.65
     Pry
    -0.65
     Hera
    -0.64
     slack
    -0.64
     torped
    -0.63
     Io
    -0.63
     Nun
    -0.62
     Scholar
    -0.61
    POSITIVE LOGITS
    iscovery
    1.28
    ynam
    1.27
    etermin
    1.24
    etermination
    1.22
    REAM
    1.21
    owntown
    1.18
    ynasty
    1.17
    rones
    1.17
    irection
    1.15
    ownt
    1.15
    Activations Density 0.067%

    No Known Activations