© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 22487
    Prev
    Next
    INDEX
    Explanations

    terms indicating infrequency or rarity

    oai_token-act-pair · gpt-3.5-turbo

    the frequency of the word "rarely."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uid
    -0.80
    arta
    -0.74
    lass
    -0.73
    hang
    -0.71
    ablishment
    -0.71
     Tags
    -0.70
    oÄŁ
    -0.70
     Redemption
    -0.69
    ermanent
    -0.68
    agate
    -0.67
    POSITIVE LOGITS
    theless
    1.07
    entimes
    1.00
     overlooked
    0.85
    pmwiki
    0.85
     underestimate
    0.83
     hesitate
    0.83
     dime
    0.78
     occas
    0.77
     forgotten
    0.76
     encountered
    0.74
    Activations Density 0.005%

    No Known Activations