© 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 EvalsExportsinterp-engineNEWAPI 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. 11577
    Prev
    Next
    INDEX
    Explanations

    references to comparisons, such as "more than," "less than," "closer to," etc

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to comparisons and categories across different subjects

    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
    =#
    -0.67
    CHAT
    -0.60
    bestos
    -0.59
    aily
    -0.58
    Accessory
    -0.58
    itone
    -0.58
    =]
    -0.57
    ='
    -0.57
    beck
    -0.57
    Fax
    -0.56
    POSITIVE LOGITS
     surveyed
    1.02
     except
    1.00
     besides
    0.90
     nowadays
    0.89
     studied
    0.86
     combined
    0.85
     imaginable
    0.83
     afloat
    0.76
     whatsoever
    0.75
     polled
    0.75
    Activations Density 0.234%

    No Known Activations