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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 7837
    Prev
    Next
    INDEX
    Explanations

    medical conditions and procedures, particularly related to eyes and sleep

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and descriptors related to eye color and various associated elements

    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
    ional
    -0.98
    ivity
    -0.87
    itatively
    -0.75
    rade
    -0.75
     municip
    -0.74
    ivism
    -0.73
    ivities
    -0.70
    Interstitial
    -0.67
     skelet
    -0.66
    izes
    -0.64
    POSITIVE LOGITS
    vironment
    0.88
    itored
    0.80
    mares
    0.77
    ewitness
    0.74
    clipse
    0.73
    unctions
    0.72
    ::::::::
    0.71
    avascript
    0.71
    hower
    0.69
    eyed
    0.69
    Activations Density 0.060%

    No Known Activations