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. 2-RES-JB
    6. 20130
    Prev
    Next
    INDEX
    Explanations

    titles of respect like "Mrs." with a person's name

    oai_token-act-pair · gpt-3.5-turbo

    references to specific women, particularly those with the title "Mrs."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Archdemon
    -0.84
    tumblr
    -0.71
    umbn
    -0.70
    ENDED
    -0.69
    CAST
    -0.67
    ucket
    -0.65
     delinquent
    -0.65
    ahime
    -0.62
     Helsinki
    -0.61
     Edinburgh
    -0.61
    POSITIVE LOGITS
    ctuary
    0.83
    icial
    0.81
     Claus
    0.80
    rha
    0.78
    glers
    0.73
    Mrs
    0.73
    cipled
    0.72
     Mrs
    0.72
    ree
    0.71
    ong
    0.67
    Activations Density 0.004%

    No Known Activations