© 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. 9381
    Prev
    Next
    INDEX
    Explanations

    information related to the brain and its development

    oai_token-act-pair · gpt-3.5-turbo

    terms related to brain anatomy and functions

    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
     Franch
    -0.90
    iversary
    -0.83
     anniversary
    -0.80
    rek
    -0.73
    ammy
    -0.73
     Anniversary
    -0.73
    ista
    -0.71
    =-=-
    -0.71
    deb
    -0.71
    pour
    -0.70
    POSITIVE LOGITS
     neurons
    1.32
     neuron
    1.15
     neuronal
    1.12
     neurotrans
    1.12
     enzymes
    1.11
     proteins
    1.08
     hypothal
    1.06
     enzyme
    1.04
     serotonin
    1.03
     regulating
    0.99
    Activations Density 0.446%

    No Known Activations