© 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. 2147
    Prev
    Next
    INDEX
    Explanations

    the word "latest"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "latest."

    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
    erved
    -0.81
    hovah
    -0.78
    avery
    -0.76
    par
    -0.76
    ships
    -0.74
    utenant
    -0.73
    wright
    -0.72
    velt
    -0.70
    krit
    -0.70
    lain
    -0.70
    POSITIVE LOGITS
     incarnation
    1.32
     installment
    1.27
     iteration
    1.20
     edition
    1.15
     round
    1.03
     developments
    0.97
     batch
    0.95
     arrivals
    0.95
     episode
    0.93
     update
    0.92
    Activations Density 0.021%

    No Known Activations