© 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. 3-RES-JB
    11. 4929
    Prev
    Next
    INDEX
    Explanations

    names and terms related to specific individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Livingston" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urities
    -0.83
    MENTS
    -0.80
    uning
    -0.75
    onies
    -0.72
    ãĥĨ
    -0.72
    unity
    -0.71
    PLA
    -0.70
    ifiable
    -0.70
    avorite
    -0.70
    ":[{"
    -0.70
    POSITIVE LOGITS
     Livingston
    0.92
    ston
    0.84
    ership
    0.75
    lov
    0.74
     Orbit
    0.74
    bourne
    0.71
     Parish
    0.70
     Wolves
    0.69
     Yard
    0.68
     Tribune
    0.65
    Activations Density 0.016%

    No Known Activations