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. 18941
    Prev
    Next
    INDEX
    Explanations

    words related to mobilization, organization, and coming together for a cause

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mobilization and organization efforts

    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
    fixed
    -0.73
    croft
    -0.71
    ble
    -0.70
    gets
    -0.68
    etheless
    -0.65
    bidden
    -0.65
     Cursed
    -0.64
    neath
    -0.64
    bey
    -0.63
    birth
    -0.63
    POSITIVE LOGITS
     mobilization
    1.14
     mobil
    0.98
    izational
    0.95
     mobilize
    0.95
    andise
    0.88
     mobilized
    0.86
    ourcing
    0.83
     GOODMAN
    0.83
    naires
    0.82
    ourced
    0.80
    Activations Density 0.016%

    No Known Activations