© 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. 963
    Prev
    Next
    INDEX
    Explanations

    terms related to non-political or non-profit entities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to non-profit organizations

    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
     Dickinson
    -0.89
     Brus
    -0.85
    ulhu
    -0.84
     Barron
    -0.79
     Rivals
    -0.76
     Royale
    -0.76
     Zup
    -0.76
     Cassidy
    -0.75
     Bam
    -0.74
     Springs
    -0.73
    POSITIVE LOGITS
    existent
    1.63
    profit
    1.30
    zero
    1.18
    inter
    1.13
    cont
    1.07
    violent
    1.07
    human
    1.06
    interest
    1.06
    governmental
    1.06
    threatening
    1.05
    Activations Density 0.039%

    No Known Activations