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. 6-RES-JB
    6. 3365
    Prev
    Next
    INDEX
    Explanations

    people's names followed by "Jr" indicating a junior generational suffix

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "Jr." (Junior) associated with names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Petraeus
    -0.72
    keeping
    -0.69
    =-=-=-=-=-=-=-=-
    -0.66
     è£ıç
    -0.65
    graduate
    -0.64
    fare
    -0.61
    point
    -0.61
    oid
    -0.61
    Front
    -0.61
    lords
    -0.60
    POSITIVE LOGITS
    .,
    0.95
    onse
    0.93
    uez
    0.90
    igne
    0.90
     Jr
    0.86
    inx
    0.86
    arcer
    0.86
    quez
    0.84
    atta
    0.80
    abba
    0.79
    Activations Density 0.015%

    No Known Activations