© 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. 6-RES-JB
    11. 2918
    Prev
    Next
    INDEX
    Explanations

    expressions related to hierarchical structuring

    oai_token-act-pair · gpt-3.5-turbo

    phrases or constructions involving possessive relationships and the word "of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.65
    fml
    -0.64
    tackle
    -0.62
    externalActionCode
    -0.59
    ](
    -0.58
    ÙIJ
    -0.58
    ,[
    -0.57
    !.
    -0.57
    achable
    -0.56
    .[
    -0.56
    POSITIVE LOGITS
     Bene
    0.63
     Nanto
    0.63
     course
    0.63
     comprises
    0.63
     consists
    0.61
    pires
    0.61
    tains
    0.58
     varies
    0.58
    aez
    0.57
     FANTASY
    0.57
    Activations Density 0.257%

    No Known Activations