© 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. 11349
    Prev
    Next
    INDEX
    Explanations

    timestamps specified in specific time zones

    oai_token-act-pair · gpt-3.5-turbo

    time zone abbreviations

    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
    keye
    -0.70
    proof
    -0.70
    izoph
    -0.67
    bor
    -0.67
    kered
    -0.67
    ffield
    -0.66
    hist
    -0.66
     resemb
    -0.64
     acknowled
    -0.63
    izations
    -0.63
    POSITIVE LOGITS
    DAQ
    0.93
     EDT
    0.88
    EMBER
    0.88
     CET
    0.83
    OSE
    0.77
    Ãī
    0.76
    ember
    0.76
     PDT
    0.75
    [/
    0.74
     +/-
    0.73
    Activations Density 0.038%

    No Known Activations