© 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. 1-RES-JB
    11. 3526
    Prev
    Next
    INDEX
    Explanations

    terms related to the industry

    oai_token-act-pair · gpt-3.5-turbo

    references to various industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0000000000000000
    -0.77
     KS
    -0.70
    pell
    -0.69
    erton
    -0.66
     Chapel
    -0.65
     rash
    -0.64
     Kw
    -0.63
     ç¥ŀ
    -0.62
    plings
    -0.61
     RR
    -0.60
    POSITIVE LOGITS
    ry
    1.25
    rious
    1.04
    ries
    1.00
    indust
    0.99
    rie
    0.94
     Indust
    0.93
    RY
    0.92
    icz
    0.89
    ī
    0.89
    ic
    0.86
    Activations Density 0.013%

    No Known Activations