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. 11-RES-JB
    6. 8698
    Prev
    Next
    INDEX
    Explanations

    comparisons in behavior or traits between different individuals

    oai_token-act-pair · gpt-3.5-turbo

    discussions related to emotional and psychological assessments in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    struction
    -0.69
    heast
    -0.68
    terday
    -0.68
    intendent
    -0.67
    externalActionCode
    -0.66
    MSN
    -0.65
    rower
    -0.65
    senal
    -0.65
    âľ
    -0.65
    era
    -0.65
    POSITIVE LOGITS
     themselves
    1.70
     strangers
    1.45
     their
    1.45
     spouses
    1.38
     THEIR
    1.26
    their
    1.23
     husbands
    1.23
     wives
    1.21
     girlfriends
    1.21
     Their
    1.14
    Activations Density 0.549%

    No Known Activations