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. 21746
    Prev
    Next
    INDEX
    Explanations

    words related to project management and descriptions of events

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to projects and their associated activities or outcomes

    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
    veland
    -0.63
    igans
    -0.55
    onest
    -0.55
    amina
    -0.54
    aples
    -0.54
    aths
    -0.53
    joice
    -0.53
    iny
    -0.52
    ierre
    -0.51
    doms
    -0.49
    POSITIVE LOGITS
     underway
    0.56
     itself
    0.53
     moot
    0.52
     Yards
    0.50
     Hoover
    0.49
     TCU
    0.45
     narrowing
    0.45
     anew
    0.45
     guiActive
    0.45
     GSL
    0.45
    Activations Density 1.958%

    No Known Activations