© 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. 5181
    Prev
    Next
    INDEX
    Explanations

    mentions of predictions, warnings, analysis, and opinions by experts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of experts and their predictions or opinions

    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
    Interstitial
    -0.80
    Complete
    -0.66
    AAAAAAAA
    -0.66
     Territories
    -0.65
    Govern
    -0.64
     manslaughter
    -0.64
    AAAA
    -0.62
    TON
    -0.59
     Warden
    -0.58
    nant
    -0.58
    POSITIVE LOGITS
    paces
    1.06
    hips
    1.02
     speculate
    1.00
    uggest
    0.97
    hran
    0.92
    ervatives
    0.91
    ervative
    0.91
    peak
    0.84
     analysts
    0.83
     alike
    0.82
    Activations Density 0.100%

    No Known Activations