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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9-RES-JB
    6. 2114
    Prev
    Next
    INDEX
    Explanations

    locations within a building such as apartment, office, residence, and room

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anson
    -0.73
    laus
    -0.73
     oneself
    -0.69
     yourselves
    -0.68
     trending
    -0.65
     themselves
    -0.62
    arnaev
    -0.59
    phabet
    -0.59
     ourselves
    -0.59
    obal
    -0.58
    POSITIVE LOGITS
    mate
    0.96
    mates
    0.94
     balcony
    0.89
     overlooking
    0.80
     porch
    0.77
    washer
    0.76
    é¾įåĸļ士
    0.75
     suite
    0.75
     driveway
    0.74
     doorway
    0.74
    Activations Density 0.181%

    No Known Activations