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. 7-RES-JB
    6. 13083
    Prev
    Next
    INDEX
    Explanations

    locations and places related to borders

    oai_token-act-pair · gpt-3.5-turbo

    geographical references and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     repertoire
    -0.71
    aughs
    -0.68
    andowski
    -0.66
     journals
    -0.64
     wardrobe
    -0.63
     hats
    -0.63
     motions
    -0.63
    erity
    -0.61
     DG
    -0.61
     pedals
    -0.61
    POSITIVE LOGITS
     suburb
    1.15
     bordering
    1.06
     northeast
    1.04
     southwest
    1.03
     annexed
    1.02
     northwest
    1.02
     southeast
    1.00
     northwestern
    0.99
     southeastern
    0.99
     southwestern
    0.98
    Activations Density 0.526%

    No Known Activations