© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 23778
    Prev
    Next
    INDEX
    Explanations

    years or dates

    oai_token-act-pair · gpt-3.5-turbo

    recurring years and dates associated with historical events or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snipp
    -0.69
    IPP
    -0.64
     Jugg
    -0.64
    Jackson
    -0.62
     pse
    -0.61
    ACTION
    -0.60
    Dialogue
    -0.59
    JP
    -0.57
    Throw
    -0.56
     Sym
    -0.56
    POSITIVE LOGITS
     onwards
    0.83
    ties
    0.74
    cards
    0.73
     onward
    0.71
    âĢ²
    0.70
    rf
    0.68
    quist
    0.65
    chel
    0.65
    mable
    0.64
    escent
    0.63
    Activations Density 0.104%

    No Known Activations