© 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. 12-RES-JB
    11. 2972
    Prev
    Next
    INDEX
    Explanations

    terms related to brain imaging techniques and brain regions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to brain structure and function

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chocobo
    -0.70
     Nare
    -0.66
     Slaughter
    -0.64
     Mankind
    -0.63
    iffe
    -0.62
     Faust
    -0.61
     Nex
    -0.61
     Bundy
    -0.59
     Corinth
    -0.58
     Crowley
    -0.58
    POSITIVE LOGITS
    stem
    1.48
    waves
    1.17
    washing
    1.14
    wave
    1.04
    washed
    1.01
    storms
    0.99
     circuitry
    0.96
     tissue
    0.88
     scans
    0.88
    iac
    0.87
    Activations Density 0.069%

    No Known Activations