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. 8-RES-JB
    6. 15834
    Prev
    Next
    INDEX
    Explanations

    street names and locations

    oai_token-act-pair · gpt-3.5-turbo

    names of locations and streets

    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
     Canaver
    -1.02
     anthrop
    -0.76
    CLAIM
    -0.69
     robot
    -0.68
    =-=-=-=-
    -0.68
     psychologist
    -0.66
     interrog
    -0.66
    omsky
    -0.65
     exorc
    -0.65
     genetically
    -0.64
    POSITIVE LOGITS
     Junction
    1.27
     Heights
    1.08
     avenues
    1.04
     Boulevard
    1.02
    opolis
    1.02
     Station
    1.01
    town
    1.00
     suburbs
    1.00
     Airport
    1.00
     Valley
    0.99
    Activations Density 0.340%

    No Known Activations