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. 8-RES-JB
    6. 19926
    Prev
    Next
    INDEX
    Explanations

    words related to specific geographical locations, specifically Sierra and Costa

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographical locations, particularly Sierra and Costa

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sworth
    -0.83
    ifier
    -0.74
    race
    -0.71
    rig
    -0.71
    soever
    -0.70
    ifiable
    -0.70
     actionGroup
    -0.69
    iple
    -0.69
    alien
    -0.68
    nl
    -0.68
    POSITIVE LOGITS
     Leone
    1.25
     Nevada
    0.92
     Scotia
    0.91
     Vista
    0.81
     Rican
    0.79
     Alto
    0.78
     Designs
    0.78
     Isles
    0.76
     footh
    0.75
    vernment
    0.73
    Activations Density 0.035%

    No Known Activations