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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 20288
    Prev
    Next
    INDEX
    Explanations

    time periods specified in years

    oai_token-act-pair · gpt-3.5-turbo

    time durations in years and periods of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iru
    -0.68
    Os
    -0.68
     Cance
    -0.67
    avascript
    -0.65
    Na
    -0.60
    opp
    -0.59
    eele
    -0.58
    Vo
    -0.58
    apo
    -0.57
    Inside
    -0.57
    POSITIVE LOGITS
     gestation
    0.78
     millennia
    0.76
     hectares
    0.76
     periods
    0.74
    waves
    0.73
     territories
    0.73
     span
    0.70
     eras
    0.69
    ahime
    0.69
     generations
    0.69
    Activations Density 0.159%

    No Known Activations