© 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. 10-RES-JB
    11. 11087
    Prev
    Next
    INDEX
    Explanations

    the name "Di" followed by a single letter

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Di."

    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
    ividual
    -0.74
    ties
    -0.72
    ï¸ı
    -0.65
    manship
    -0.63
    æĢ
    -0.62
    icators
    -0.61
     recess
    -0.61
    stretched
    -0.61
     trivia
    -0.61
     hire
    -0.60
    POSITIVE LOGITS
    abol
    1.34
    ploma
    1.33
    agonal
    1.26
    abolic
    1.25
    abetic
    1.25
    agram
    1.22
    plom
    1.21
    urnal
    1.21
    abetes
    1.20
    ocese
    1.19
    Activations Density 0.013%

    No Known Activations