© 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. 22881
    Prev
    Next
    INDEX
    Explanations

    words related to physical locations or geography

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to sexual content or innuendos

    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
    STER
    -0.78
     Keynes
    -0.77
     808
    -0.72
    kj
    -0.68
    ted
    -0.67
    giving
    -0.67
     Kers
    -0.65
     Hyde
    -0.63
    frame
    -0.61
    gets
    -0.60
    POSITIVE LOGITS
    adian
    1.35
    asc
    1.31
    adia
    1.23
    itri
    1.08
    urred
    1.07
    idal
    1.02
    ocious
    1.00
    adem
    0.99
    ribed
    0.99
    endant
    0.98
    Activations Density 0.007%

    No Known Activations