© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5341
    Prev
    Next
    INDEX
    Explanations

    expressions related to being a representative or representing someone or something

    oai_token-act-pair · gpt-3.5-turbo

    terms or phrases indicating representation or representatives in various contexts

    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
    frey
    -0.94
    bows
    -0.90
    awar
    -0.85
    imb
    -0.83
    yard
    -0.82
    aughs
    -0.82
    forth
    -0.81
    osure
    -0.79
    stead
    -0.71
     Spit
    -0.71
    POSITIVE LOGITS
     representative
    0.93
    soType
    0.91
     representatives
    0.81
     android
    0.79
     Kislyak
    0.76
     antioxid
    0.74
    holder
    0.70
     warr
    0.69
    rored
    0.68
    ority
    0.67
    Activations Density 0.009%

    No Known Activations