© 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. 1309
    Prev
    Next
    INDEX
    Explanations

    references to science fiction author names

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "ro"

    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
     innocence
    -0.63
     fet
    -0.62
     Catalyst
    -0.60
     HDL
    -0.60
     Username
    -0.59
     controversial
    -0.57
     htt
    -0.57
     WARN
    -0.56
     amnesty
    -0.56
     signific
    -0.55
    POSITIVE LOGITS
    cks
    1.26
    vs
    1.15
    tto
    1.13
    bably
    1.12
    phy
    1.11
    chemical
    1.10
    dden
    1.10
    tt
    1.09
    ds
    1.05
    scope
    1.05
    Activations Density 0.045%

    No Known Activations