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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 20488
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or proper nouns related to the name "Irving."

    oai_token-act-pair · gpt-3.5-turbo

    the name "Irving" and related mentions in various contexts

    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
    strip
    -0.92
    wcsstore
    -0.90
    emon
    -0.89
    llular
    -0.89
    emonic
    -0.87
    ombat
    -0.84
    organic
    -0.80
    ework
    -0.80
    zee
    -0.79
    ococ
    -0.78
    POSITIVE LOGITS
     Irving
    1.01
     Berlin
    0.85
    WER
    0.76
     Hayward
    0.75
     GER
    0.72
    stadt
    0.70
    burgh
    0.70
     Clifford
    0.69
    onne
    0.69
     Krist
    0.66
    Activations Density 0.029%

    No Known Activations