© 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. 8404
    Prev
    Next
    INDEX
    Explanations

    phrases related to exploration or the edge of known areas

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Frontier" and related terms

    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
     Sass
    -0.69
    henko
    -0.69
     nails
    -0.64
     spray
    -0.64
    onse
    -0.64
     vit
    -0.64
    DERR
    -0.62
     $_
    -0.62
     pots
    -0.61
     baking
    -0.61
    POSITIVE LOGITS
     Frontier
    4.28
     frontier
    1.92
     Horizons
    1.13
    Front
    1.11
     Pione
    1.10
     Elite
    1.09
     Horizon
    1.06
     Front
    1.05
     Colony
    1.03
     Southwest
    1.01
    Activations Density 0.020%

    No Known Activations