© 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. 9-RES-JB
    11. 16394
    Prev
    Next
    INDEX
    Explanations

    references to historical dates or time periods

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to historical timelines or origins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hold
    -0.66
    iasis
    -0.63
    otos
    -0.63
    quit
    -0.63
    talk
    -0.62
     bil
    -0.61
    squ
    -0.61
    ulla
    -0.60
    mare
    -0.60
    eye
    -0.60
    POSITIVE LOGITS
    ĸļ
    0.71
     âĸĪ
    0.70
     antiquity
    0.70
    encing
    0.65
    bris
    0.65
    Orig
    0.64
    ences
    0.63
     Dating
    0.62
     upwards
    0.61
    âĸĪâĸĪ
    0.61
    Activations Density 0.030%

    No Known Activations