© 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. 7337
    Prev
    Next
    INDEX
    Explanations

    instances of 'major' events or achievements

    oai_token-act-pair · gpt-3.5-turbo

    mentions of significant milestones or first occurrences in various contexts

    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
    utics
    -0.70
     Petra
    -0.67
     abound
    -0.67
     Osiris
    -0.66
    asty
    -0.66
    terness
    -0.65
    tnc
    -0.64
    bes
    -0.64
    hoe
    -0.63
    lain
    -0.63
    POSITIVE LOGITS
     foray
    0.96
     outing
    0.92
     casualty
    0.81
     imaginable
    0.80
     sighting
    0.80
     ever
    0.80
     hurdle
    0.78
     attempt
    0.78
    istani
    0.75
     introdu
    0.72
    Activations Density 0.173%

    No Known Activations