© 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. 3-RES-JB
    11. 23597
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to chemical compounds or substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.96
    utenant
    -0.82
    HCR
    -0.77
     Crowd
    -0.77
    culosis
    -0.73
    tsky
    -0.72
     Provider
    -0.69
    ULTS
    -0.69
    OHN
    -0.69
    OAD
    -0.69
    POSITIVE LOGITS
    agonal
    1.37
     hex
    1.12
    agon
    1.06
    hex
    1.06
    agons
    0.92
    dump
    0.90
    etr
    0.90
    iated
    0.87
     Hex
    0.87
    ile
    0.84
    Activations Density 0.011%

    No Known Activations