© 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. 10204
    Prev
    Next
    INDEX
    Explanations

    places or situations where individuals can go in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate lack of direction or options

    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
    advertisement
    -0.72
    ĸļ
    -0.69
    soDeliveryDate
    -0.69
    naires
    -0.67
     Respons
    -0.65
     wrinkles
    -0.64
    creator
    -0.64
    lore
    -0.62
    requires
    -0.62
     Conan
    -0.62
    POSITIVE LOGITS
     locate
    1.09
     reside
    1.06
     stash
    0.98
     find
    0.95
     go
    0.94
     hide
    0.93
     store
    0.86
     congreg
    0.85
     practise
    0.84
     refuel
    0.84
    Activations Density 0.075%

    No Known Activations