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

    Neuronpedia

    APICircuit 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. 8-RES-JB
    6. 4701
    Prev
    Next
    INDEX
    Explanations

    specific time references, such as dates and periods, indicating a specific point in time

    oai_token-act-pair · gpt-3.5-turbo

    temporal markers indicating progression in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imir
    -0.77
    apixel
    -0.72
    uras
    -0.67
    ibaba
    -0.64
    arij
    -0.64
    artifacts
    -0.64
    jri
    -0.63
    licted
    -0.63
    criptions
    -0.61
    ARI
    -0.60
    POSITIVE LOGITS
     2025
    0.73
     standards
    0.71
     exhaustion
    0.70
     2030
    0.69
    rox
    0.66
     2050
    0.65
     arriving
    0.65
    Closure
    0.64
    stocks
    0.63
     maturity
    0.62
    Activations Density 0.083%

    No Known Activations