Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 8066
    Prev
    Next
    INDEX
    Explanations

    references to events or actions that occurred in the past

    oai_token-act-pair · gpt-3.5-turbo

    references to the past, specifically phrases involving the word "then."

    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
    ting
    -0.74
    toe
    -0.70
    pace
    -0.67
    icles
    -0.64
    assed
    -0.64
    kson
    -0.64
    chy
    -0.62
    mission
    -0.60
    icle
    -0.60
    cott
    -0.59
    POSITIVE LOGITS
    Ń·
    0.81
    ©¶æ
    0.76
    vernment
    0.72
     compr
    0.69
    ceed
    0.65
    ÃĥÃĤ
    0.65
    velength
    0.64
    ividual
    0.64
    veland
    0.64
     proceeded
    0.63
    Activations Density 0.046%

    No Known Activations