© 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. 6-RES-JB
    11. 5463
    Prev
    Next
    INDEX
    Explanations

    news agencies mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to news agencies

    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
    çļ
    -0.87
    âķIJ
    -0.78
    gro
    -0.75
    çĶŁ
    -0.74
    benef
    -0.70
    artisan
    -0.70
    adow
    -0.68
    gage
    -0.67
    urden
    -0.67
    benefit
    -0.67
    POSITIVE LOGITS
     AFP
    0.73
     quoted
    0.70
     Ltd
    0.69
    INESS
    0.67
     messenger
    0.66
     Sport
    0.64
     outlet
    0.64
     Osiris
    0.63
     quoting
    0.63
     Xin
    0.62
    Activations Density 0.056%

    No Known Activations