© 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. 7-RES-JB
    11. 12452
    Prev
    Next
    INDEX
    Explanations

    physical descriptions of people

    oai_token-act-pair · gpt-3.5-turbo

    physical descriptions of individuals including height, weight, and appearance features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OUP
    -0.78
    arten
    -0.74
    icals
    -0.72
    opol
    -0.70
     SOS
    -0.69
     Reader
    -0.69
     DRM
    -0.69
    policy
    -0.69
     Safe
    -0.69
    nesday
    -0.69
    POSITIVE LOGITS
     protr
    1.32
     slender
    1.18
     elong
    1.15
     muscular
    1.12
     torso
    1.11
     stature
    1.10
     humanoid
    1.09
     tallest
    1.08
     weighs
    1.05
     taller
    1.04
    Activations Density 0.558%

    No Known Activations