Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 5288
    Prev
    Next
    INDEX
    Explanations

    the name "Katie" followed by a single letter or a surname

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Katie" or similar variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dfx
    -0.85
    interstitial
    -0.82
    ional
    -0.81
    reed
    -0.81
    lict
    -0.80
    netflix
    -0.79
    istry
    -0.76
    asks
    -0.73
    itent
    -0.73
    pmwiki
    -0.72
    POSITIVE LOGITS
    Kat
    1.01
     Cour
    0.98
     Pav
    0.93
     Katie
    0.88
     Nolan
    0.87
     Holmes
    0.84
    kat
    0.84
     Upton
    0.83
    rina
    0.82
     Hopkins
    0.81
    Activations Density 0.007%

    No Known Activations