© 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. 9495
    Prev
    Next
    INDEX
    Explanations

    timestamps in GMT format

    oai_token-act-pair · gpt-3.5-turbo

    mentions of time zone indicators

    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
    pton
    -0.72
    bor
    -0.71
    duct
    -0.70
    sbm
    -0.68
    Kin
    -0.67
    bryce
    -0.66
    ply
    -0.66
    shared
    -0.65
    kus
    -0.64
    pron
    -0.62
    POSITIVE LOGITS
     GMT
    0.82
    /+
    0.79
     (+
    0.78
    +
    0.69
     Pavilion
    0.68
    legraph
    0.68
    ounge
    0.67
     Entry
    0.66
     CET
    0.66
    UE
    0.66
    Activations Density 0.016%

    No Known Activations