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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 10-RES-JB
    6. 8788
    Prev
    Next
    INDEX
    Explanations

    locations or places based on the context

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ragon
    -0.70
    izu
    -0.66
    ivot
    -0.66
    unning
    -0.66
    Secondly
    -0.65
    telling
    -0.65
    akening
    -0.65
    qus
    -0.65
    reg
    -0.64
    mind
    -0.64
    POSITIVE LOGITS
     they
    1.01
    soever
    0.97
     he
    0.86
     she
    0.80
    upon
    0.77
     we
    0.77
     protesters
    0.71
     thousands
    0.70
     abortions
    0.69
     terrorists
    0.67
    Activations Density 0.066%

    No Known Activations