© 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. 2-RES-JB
    11. 11967
    Prev
    Next
    INDEX
    Explanations

    individuals or objects that are specifically highlighted or selected from a group

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "singled" or variations of "single."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITNESS
    -0.87
     Tycoon
    -0.84
    soDeliveryDate
    -0.67
     Universe
    -0.62
    endi
    -0.62
    wives
    -0.61
     Mayo
    -0.60
    natureconservancy
    -0.59
    pir
    -0.59
    DX
    -0.59
    POSITIVE LOGITS
     singled
    1.22
    otom
    0.85
    ouble
    0.80
    gment
    0.78
    tle
    0.76
    pard
    0.74
    bage
    0.72
    handedly
    0.72
    ented
    0.70
    bered
    0.70
    Activations Density 0.006%

    No Known Activations