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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-RES-JB
    6. 17156
    Prev
    Next
    INDEX
    Explanations

    the most recent or up-to-date information or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "latest" in context with reports or developments

    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
    avery
    -0.80
    erved
    -0.75
    hovah
    -0.74
    velt
    -0.74
    oak
    -0.73
    par
    -0.72
    aldehyde
    -0.71
    dinand
    -0.70
    krit
    -0.68
    ships
    -0.68
    POSITIVE LOGITS
     incarnation
    1.25
     iteration
    1.20
     installment
    1.16
     edition
    1.08
     developments
    0.92
     arrivals
    0.91
     round
    0.90
     episode
    0.89
     batch
    0.88
     update
    0.87
    Activations Density 0.016%

    No Known Activations