© 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. 2-RES-JB
    11. 14880
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Erikson" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly "Erikson" and "Rickson"

    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
     defe
    -0.72
    Cod
    -0.70
    BIL
    -0.66
     miscarriage
    -0.64
     Columb
    -0.64
     leukemia
    -0.63
     pancreat
    -0.63
    abetic
    -0.62
    ENTION
    -0.62
     clipboard
    -0.62
    POSITIVE LOGITS
    haw
    1.18
    riks
    1.04
    ules
    0.98
    lander
    0.98
    stad
    0.96
    kson
    0.95
    wagen
    0.91
    hots
    0.89
    ham
    0.85
    gaard
    0.85
    Activations Density 0.016%

    No Known Activations