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. 3-RES-JB
    6. 7828
    Prev
    Next
    INDEX
    Explanations

    words related to the surname "Berg"

    oai_token-act-pair · gpt-3.5-turbo

    names associated with a specific individual, likely someone notable or influential in a particular context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LEASE
    -0.73
    eer
    -0.69
    eering
    -0.68
     Samoa
    -0.66
     variance
    -0.65
     Pinterest
    -0.64
     prevailing
    -0.64
    phis
    -0.62
    ————
    -0.62
    */(
    -0.62
    POSITIVE LOGITS
    quist
    1.14
    strom
    1.13
    ogl
    1.10
    sten
    1.06
     Berg
    1.06
    kamp
    1.02
    stein
    1.01
    qv
    0.99
    mann
    0.99
    liga
    0.98
    Activations Density 0.009%

    No Known Activations