© 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. 2-RES-JB
    6. 18802
    Prev
    Next
    INDEX
    Explanations

    references to the concept of 'passage', such as the passage of time or the passage of a law

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "passage" related to legislative or formal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tur
    -0.65
    wig
    -0.65
    grave
    -0.64
    ches
    -0.64
    rum
    -0.63
    ched
    -0.63
     Wast
    -0.62
     desserts
    -0.60
     soil
    -0.59
     Fir
    -0.59
    POSITIVE LOGITS
     passage
    1.07
     passages
    0.85
    phrase
    0.84
     Passed
    0.82
    enger
    0.77
    smanship
    0.77
    dayName
    0.74
    代
    0.73
    forward
    0.71
    acement
    0.70
    Activations Density 0.005%

    No Known Activations