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. 8921
    Prev
    Next
    INDEX
    Explanations

    significant events throughout history

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of history

    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
    */(
    -0.84
    nets
    -0.79
    jab
    -0.77
    pload
    -0.75
    reau
    -0.70
    utan
    -0.70
    hap
    -0.69
    liga
    -0.68
    atum
    -0.67
    forward
    -0.65
    POSITIVE LOGITS
     mankind
    0.77
     warfare
    0.74
     Warfare
    0.71
     sorts
    0.70
     course
    0.70
     Humanity
    0.68
     humankind
    0.67
     heroism
    0.67
     PROG
    0.67
     Belief
    0.65
    Activations Density 0.163%

    No Known Activations