© 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. 13250
    Prev
    Next
    INDEX
    Explanations

    references to the word "serpent"

    oai_token-act-pair · gpt-3.5-turbo

    references to series or episodes

    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
    INGTON
    -0.85
    hetti
    -0.79
    ESCO
    -0.77
    enegger
    -0.75
    ORN
    -0.75
    OWS
    -0.72
    ITNESS
    -0.72
    ORED
    -0.71
    PUT
    -0.69
    STEP
    -0.69
    POSITIVE LOGITS
    ials
    1.08
    geant
    1.06
    iffs
    0.87
    ogly
    0.87
     confir
    0.86
     encount
    0.81
    iously
    0.80
    imony
    0.79
     ser
    0.79
    mons
    0.78
    Activations Density 0.009%

    No Known Activations