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. 1-RES-JB
    6. 19035
    Prev
    Next
    INDEX
    Explanations

    references to the city of Los Angeles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Los Angeles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perature
    -0.73
    Ü
    -0.69
    udeb
    -0.68
    minded
    -0.67
    urtle
    -0.67
    weak
    -0.65
    displayText
    -0.65
    arget
    -0.65
    addons
    -0.64
    tle
    -0.64
    POSITIVE LOGITS
     Angeles
    1.68
     Unified
    0.99
     Lakers
    0.96
     Lumpur
    0.95
     ANGEL
    0.93
     County
    0.89
     Dodgers
    0.88
     Clippers
    0.87
     Times
    0.86
    izabeth
    0.84
    Activations Density 0.014%

    No Known Activations