© 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. 6-RES-JB
    11. 7786
    Prev
    Next
    INDEX
    Explanations

    long strings of characters marked by symbols

    oai_token-act-pair · gpt-3.5-turbo

    instances of the tilde symbol (~)

    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
     Dynamics
    -0.82
     Luther
    -0.72
     Jinn
    -0.72
    iasis
    -0.66
     Bulgar
    -0.65
     implant
    -0.65
     bearer
    -0.65
     photoc
    -0.64
     modification
    -0.64
    iant
    -0.63
    POSITIVE LOGITS
    =~=~
    1.40
    #$
    1.00
    ãģ¦
    0.83
    sil
    0.83
    GW
    0.81
    ã
    0.81
    LI
    0.80
    _-
    0.79
    rules
    0.78
    $
    0.77
    Activations Density 0.023%

    No Known Activations