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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 21589
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific location named "Salinas"

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "Salinas" and its variations

    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
     ful
    -0.62
     resistance
    -0.62
     overt
    -0.61
     overrun
    -0.61
     Written
    -0.60
     cont
    -0.58
     conscientious
    -0.56
     Change
    -0.56
     agent
    -0.56
     change
    -0.55
    POSITIVE LOGITS
    inas
    5.05
    ina
    1.82
    inos
    1.64
    inis
    1.56
    inian
    1.48
    INA
    1.37
    inar
    1.31
    inia
    1.29
    ines
    1.25
    ino
    1.21
    Activations Density 0.004%

    No Known Activations