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. 4-RES-JB
    6. 3011
    Prev
    Next
    INDEX
    Explanations

    words related to freelance work and activism

    oai_token-act-pair · gpt-3.5-turbo

    references to freelance work or freelancers

    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
    AppData
    -0.98
    ĪĴ
    -0.80
    ä¸ī
    -0.78
     Moons
    -0.74
    ²¾
    -0.73
    è£
    -0.71
    »Ĵ
    -0.71
     magnification
    -0.70
    ccording
    -0.70
     fluor
    -0.67
    POSITIVE LOGITS
    heit
    1.00
    iland
    1.00
    anding
    0.86
    arters
    0.85
    enhagen
    0.80
    esse
    0.80
    cest
    0.80
    hirt
    0.80
    inki
    0.78
    idad
    0.76
    Activations Density 0.065%

    No Known Activations