© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 4439
    Prev
    Next
    INDEX
    Explanations

    terms related to the brain

    oai_token-act-pair · gpt-3.5-turbo

    references to the brain and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Arabian
    -0.75
     Prosecut
    -0.70
     Arabia
    -0.68
     Rhod
    -0.63
     Ascend
    -0.63
     Antiqu
    -0.63
     Beckham
    -0.62
     Rhodes
    -0.62
     Navajo
    -0.60
     Ryder
    -0.60
    POSITIVE LOGITS
    wash
    1.18
    washed
    1.09
    stem
    1.07
    fuck
    1.03
    washing
    1.02
    iac
    0.95
    share
    0.92
    storms
    0.91
    hov
    0.91
    child
    0.89
    Activations Density 0.019%

    No Known Activations