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. 3-RES-JB
    6. 7327
    Prev
    Next
    INDEX
    Explanations

    locations on the outskirts or periphery

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geographic locations on the outskirts or periphery of areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alogue
    -0.76
     submar
    -0.72
    channelAvailability
    -0.70
    Lear
    -0.69
    apego
    -0.65
    ombs
    -0.64
    KEY
    -0.63
    Chuck
    -0.62
    DN
    -0.62
    ANN
    -0.62
    POSITIVE LOGITS
     outskirts
    0.91
     perimeter
    0.71
    side
    0.70
    cape
    0.68
    chool
    0.66
     EntityItem
    0.66
    abouts
    0.65
     town
    0.65
     suburb
    0.65
    cloth
    0.64
    Activations Density 0.012%

    No Known Activations