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. 0-RES-JB
    6. 17340
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific locations, such as "Beverly" and "Pasadena."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific locations or cities, particularly those in California

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zik
    -0.86
     Wolves
    -0.80
     Titan
    -0.76
     Moose
    -0.72
     PKK
    -0.72
     Golem
    -0.71
     memes
    -0.71
    react
    -0.70
     minion
    -0.70
    mining
    -0.69
    POSITIVE LOGITS
     Beverly
    3.74
     Pasadena
    1.76
     Venice
    1.41
    ibu
    1.29
     Jackie
    1.21
     LAPD
    1.21
     Sandra
    1.19
     Gloria
    1.17
     Bever
    1.15
     affirmative
    1.14
    Activations Density 0.043%

    No Known Activations