© 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. 14488
    Prev
    Next
    INDEX
    Explanations

    names, particularly surnames

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Riley" and "Rae."

    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
    ablishment
    -0.88
    ropolitan
    -0.82
    alion
    -0.77
    itably
    -0.76
    dayName
    -0.75
    ÑĢ
    -0.75
    orate
    -0.67
    RON
    -0.67
    iliary
    -0.66
    ÑĮ
    -0.65
    POSITIVE LOGITS
     Riley
    1.18
    tti
    0.82
    inois
    0.79
    ieri
    0.78
    senal
    0.77
    otti
    0.75
    backer
    0.75
    boro
    0.74
     Pace
    0.72
    bee
    0.72
    Activations Density 0.005%

    No Known Activations