© 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. 8-RES-JB
    11. 22360
    Prev
    Next
    INDEX
    Explanations

    numerical values related to measurements, statistics, and figures

    oai_token-act-pair · gpt-3.5-turbo

    numerical figures, particularly related to quantities and statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sterdam
    -0.79
    ulhu
    -0.79
    apolis
    -0.71
    shake
    -0.69
    actic
    -0.69
    fare
    -0.69
    krit
    -0.67
    arnaev
    -0.65
    awa
    -0.64
    ablishment
    -0.63
    POSITIVE LOGITS
    lbs
    0.86
    ãĥ©ãĥ³
    0.77
     lbs
    0.76
    ocity
    0.76
     pounds
    0.75
    px
    0.75
     calories
    0.74
    bably
    0.72
    essed
    0.69
    utive
    0.67
    Activations Density 0.073%

    No Known Activations