© 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. 10244
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically surnames

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix "ker" in various contexts

    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
    UME
    -0.68
     historic
    -0.65
     extreme
    -0.64
     stringent
    -0.62
     strict
    -0.61
     Iranian
    -0.60
     repressive
    -0.59
    UE
    -0.59
     forbidden
    -0.58
     haste
    -0.58
    POSITIVE LOGITS
    ker
    1.26
    chief
    1.09
    kers
    1.00
    luster
    0.92
    lund
    0.84
    wagen
    0.84
    icker
    0.83
    borg
    0.83
    daq
    0.82
    holm
    0.81
    Activations Density 0.004%

    No Known Activations