© 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. 11-RES-JB
    11. 6864
    Prev
    Next
    INDEX
    Explanations

    phrases related to questioning reasons or justifications

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the"

    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
    ourced
    -0.70
    chers
    -0.64
     respectively
    -0.63
    posal
    -0.62
    isin
    -0.61
    iam
    -0.61
    ARI
    -0.61
    isf
    -0.60
    ale
    -0.59
    share
    -0.59
    POSITIVE LOGITS
     slightest
    1.60
     meantime
    1.10
     absence
    1.00
     sense
    1.00
     midst
    0.99
     shortest
    0.97
     foreseeable
    0.97
     least
    0.96
     simplest
    0.95
     fullest
    0.94
    Activations Density 0.150%

    No Known Activations