© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 837
    Prev
    Next
    INDEX
    Explanations

    the phrase "on the eve of"

    oai_token-act-pair · gpt-4-turbo

    events happening on the eve of something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "eve" in various contexts

    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
    opted
    -0.70
    IED
    -0.69
    mel
    -0.67
    MAG
    -0.63
    ector
    -0.61
    ondo
    -0.60
    odium
    -0.60
    headed
    -0.59
    outed
    -0.59
    devices
    -0.59
    POSITIVE LOGITS
     eve
    1.23
     Eve
    0.90
    cape
    0.84
    rette
    0.82
    uary
    0.80
    odox
    0.75
    lyn
    0.73
    terday
    0.73
    ete
    0.72
    cffff
    0.70
    Activations Density 0.004%

    No Known Activations