© 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. 16971
    Prev
    Next
    INDEX
    Explanations

    references to historical or chronological dating

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words related to historical timelines and origins

    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
    eye
    -0.76
    reet
    -0.73
    ucky
    -0.72
    osta
    -0.71
    owa
    -0.71
    allah
    -0.70
    alion
    -0.68
    otos
    -0.67
    itol
    -0.67
    aucus
    -0.67
    POSITIVE LOGITS
     Dating
    0.82
    dating
    0.64
     dated
    0.64
    encing
    0.64
     dating
    0.63
    entially
    0.62
    mers
    0.61
     âĸĪ
    0.61
    enance
    0.60
     Reconstruction
    0.60
    Activations Density 0.023%

    No Known Activations