© 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. 10099
    Prev
    Next
    INDEX
    Explanations

    height and weight measurements expressed in feet and pounds

    oai_token-act-pair · gpt-3.5-turbo

    numerical representations of height and weight

    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
     Mechdragon
    -0.74
     Psy
    -0.67
     prob
    -0.65
     Proc
    -0.64
     Prometheus
    -0.63
     schedules
    -0.61
     bachelor
    -0.61
     Foss
    -0.60
     physic
    -0.60
     emot
    -0.58
    POSITIVE LOGITS
    tall
    1.25
    long
    1.08
    plus
    1.08
    radius
    1.07
    sized
    1.06
    eight
    1.06
    inches
    1.03
    per
    1.02
    wide
    1.01
    inch
    1.01
    Activations Density 0.056%

    No Known Activations