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. 0-RES-JB
    6. 8938
    Prev
    Next
    INDEX
    Explanations

    references to the geographical location "Montana"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Montana"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĶĢâĶĢ
    -0.77
    ysc
    -0.76
    Toy
    -0.74
    Shin
    -0.67
     Rei
    -0.67
    alled
    -0.66
    abi
    -0.65
     cylinder
    -0.64
    INAL
    -0.63
     Kinect
    -0.63
    POSITIVE LOGITS
     Montana
    3.93
    Mont
    1.76
     Wyoming
    1.66
     Idaho
    1.63
     Yellowstone
    1.63
     Alaska
    1.46
     Boise
    1.39
     Glacier
    1.38
     Nebraska
    1.38
     Nevada
    1.38
    Activations Density 0.023%

    No Known Activations