© 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. 10-RES-JB
    11. 11535
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical sizes and measurements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to demographics and social classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    redients
    -1.03
    abilities
    -1.03
    ernels
    -0.90
    lations
    -0.89
    awatts
    -0.88
    ptoms
    -0.88
    stals
    -0.86
     aliases
    -0.86
    xes
    -0.84
    isites
    -0.84
    POSITIVE LOGITS
     person
    1.08
     guy
    1.06
     standpoint
    1.05
     athlete
    0.93
     situation
    0.92
     organism
    0.91
     paycheck
    0.90
     opponent
    0.90
     lover
    0.89
     politician
    0.88
    Activations Density 0.507%

    No Known Activations