© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 14941
    Prev
    Next
    INDEX
    Explanations

    words related to quantity or intensity

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating abundance or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aves
    -0.87
    agents
    -0.87
    oops
    -0.86
    Ts
    -0.83
    adas
    -0.82
    aunts
    -0.79
    ares
    -0.79
    opers
    -0.78
    ãĥ¼ãĥ³
    -0.77
    gements
    -0.75
    POSITIVE LOGITS
     overlap
    1.29
     disagreement
    1.26
     ambiguity
    1.18
     unanim
    1.10
     variability
    1.10
     confusion
    1.08
     difference
    1.06
     similarity
    1.06
     irony
    1.06
     inconsistency
    1.06
    Activations Density 0.156%

    No Known Activations