© 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. 3-RES-JB
    11. 9166
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals in a position of a trainer

    oai_token-act-pair · gpt-3.5-turbo

    references to trainers and instructors

    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
    shall
    -0.69
    mits
    -0.69
    izons
    -0.69
    eous
    -0.67
    itous
    -0.67
    eda
    -0.67
    sent
    -0.66
    itals
    -0.65
    itional
    -0.64
    atos
    -0.64
    POSITIVE LOGITS
     trainer
    1.10
     trainers
    0.97
     Trainer
    0.94
    charg
    0.73
    Card
    0.71
     instructor
    0.70
     instructors
    0.69
    Skip
    0.67
    ="#
    0.65
    heses
    0.64
    Activations Density 0.015%

    No Known Activations