© 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. 9-RES-JB
    11. 15565
    Prev
    Next
    INDEX
    Explanations

    historical and religious figures' names

    oai_token-act-pair · gpt-3.5-turbo

    historical figures and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tools
    -0.72
    malink
    -0.70
    ratom
    -0.70
    feature
    -0.70
    rador
    -0.70
    Wisconsin
    -0.68
    machine
    -0.68
    REAM
    -0.67
    FU
    -0.67
    LOAD
    -0.67
    POSITIVE LOGITS
     Galile
    1.22
     XVI
    1.20
     Augustus
    1.19
     Herod
    1.18
     VIII
    1.16
     Tud
    1.15
     Claud
    1.13
     Romans
    1.13
     XIV
    1.12
     XII
    1.12
    Activations Density 0.244%

    No Known Activations