© 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. 0-RES-JB
    11. 2210
    Prev
    Next
    INDEX
    Explanations

    scientific or medical terminology related to psychology and neurophysiology

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with psychology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sinks
    -0.70
     belts
    -0.67
     installs
    -0.64
     seals
    -0.64
     weld
    -0.64
     warning
    -0.63
     Advertisement
    -0.62
     disclaim
    -0.62
     tiles
    -0.61
     docks
    -0.61
    POSITIVE LOGITS
    psy
    4.71
    Psy
    1.91
     Psy
    1.47
    ps
    1.43
    psych
    1.28
    pse
    1.23
    ptic
    1.22
     psy
    1.21
    Psych
    1.17
     Psycho
    1.16
    Activations Density 0.008%

    No Known Activations