© 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. 651
    Prev
    Next
    INDEX
    Explanations

    words containing the suffix "late" or "lated"

    oai_token-act-pair · gpt-4-turbo

    terms related to inflation or increasing values

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "late" and its derivatives

    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
    orial
    -0.83
    hold
    -0.82
    ciation
    -0.74
    cade
    -0.72
    fml
    -0.68
    aido
    -0.66
    ongs
    -0.65
     liking
    -0.65
    raint
    -0.65
    SUP
    -0.64
    POSITIVE LOGITS
    late
    0.91
    uated
    0.89
    glers
    0.82
    uating
    0.81
    orescent
    0.77
    udicrous
    0.75
    lated
    0.73
    rating
    0.72
     inflated
    0.72
    uations
    0.72
    Activations Density 0.019%

    No Known Activations