© 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. 278
    Prev
    Next
    INDEX
    Explanations

    phrases related to statements made by a specific person

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "he" in the text

    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
     Measure
    -0.63
     miscarriage
    -0.62
     cubic
    -0.59
     Skull
    -0.58
     Powered
    -0.56
     cannabin
    -0.56
     Omega
    -0.55
     Everywhere
    -0.55
     Domain
    -0.55
     womb
    -0.55
    POSITIVE LOGITS
    zbollah
    1.13
     argued
    1.12
     reasoned
    1.09
     explained
    1.08
     said
    1.07
    eding
    1.06
     remarked
    1.05
     added
    1.04
     contended
    1.03
     asserted
    1.03
    Activations Density 0.069%

    No Known Activations