© 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. 10346
    Prev
    Next
    INDEX
    Explanations

    words related to the ability to differentiate or distinguish between things

    oai_token-act-pair · gpt-3.5-turbo

    terms related to distinguishing or differentiating between categories or objects

    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
    oil
    -0.69
    nz
    -0.65
     roller
    -0.62
    odd
    -0.62
     Omni
    -0.60
    rollers
    -0.59
    MN
    -0.59
    eden
    -0.59
    wives
    -0.58
    md
    -0.57
    POSITIVE LOGITS
    ively
    1.08
    iates
    0.95
    ĨĴ
    0.94
    iveness
    0.93
     warr
    0.91
     distinctions
    0.86
    iating
    0.86
     distinguishing
    0.85
    ĸļ
    0.84
     distinguish
    0.84
    Activations Density 0.023%

    No Known Activations