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. 7-RES-JB
    6. 15168
    Prev
    Next
    INDEX
    Explanations

    information related to debates, conflicts, and agreements between individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to political candidates and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phies
    -0.83
    ogle
    -0.78
    pletion
    -0.76
    kie
    -0.75
    akery
    -0.73
    anson
    -0.71
    aunder
    -0.69
    anyl
    -0.69
    arte
    -0.69
    uta
    -0.68
    POSITIVE LOGITS
     mutually
    1.49
     insepar
    1.15
     halves
    1.11
     differing
    1.11
     respectively
    1.09
     together
    1.06
     respective
    1.06
     jointly
    1.05
     Together
    0.99
     sexes
    0.99
    Activations Density 1.089%

    No Known Activations