© 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 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. 9-RES-JB
    11. 16039
    Prev
    Next
    INDEX
    Explanations

    references to BR in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the string "BR" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eers
    -0.68
     Patrol
    -0.66
    rers
    -0.66
     Gutenberg
    -0.64
     FTA
    -0.63
     Scientology
    -0.62
     fusion
    -0.58
     subsistence
    -0.57
    arial
    -0.57
    mons
    -0.57
    POSITIVE LOGITS
    OAD
    1.24
    OOK
    1.14
    anch
    1.09
    iggs
    1.08
    ackets
    1.02
    OCK
    1.02
    ICK
    1.02
    acket
    1.01
    OTHER
    0.98
    OWN
    0.96
    Activations Density 0.020%

    No Known Activations