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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 1631
    Prev
    Next
    INDEX
    Explanations

    words related to the city or location "Limerick."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Lim" 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
    ALK
    -0.73
    ãĤº
    -0.70
     Racial
    -0.69
    ãĤ«
    -0.67
    ãģį
    -0.67
    Kent
    -0.63
    ãĤ¢ãĥ«
    -0.63
    WD
    -0.63
    ãģ®éŃĶ
    -0.62
     IMAGES
    -0.62
    POSITIVE LOGITS
    itations
    1.13
    elight
    1.10
    erick
    1.06
    bered
    1.05
    psons
    1.01
    ogy
    0.97
    ajo
    0.96
    inished
    0.94
    igree
    0.90
    itation
    0.89
    Activations Density 0.012%

    No Known Activations