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. 9-RES-JB
    6. 2203
    Prev
    Next
    INDEX
    Explanations

    a role associated with representing others, potentially in a political or official capacity

    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
    osure
    -0.87
    seed
    -0.73
    fters
    -0.73
    strap
    -0.72
    imb
    -0.70
    tered
    -0.70
    INESS
    -0.69
     Pound
    -0.67
     [|
    -0.67
    istically
    -0.66
    POSITIVE LOGITS
    hips
    0.96
     Kislyak
    0.87
    clinton
    0.81
    atures
    0.79
    onse
    0.78
    ority
    0.75
    akes
    0.75
    OTUS
    0.74
     warr
    0.72
    orial
    0.69
    Activations Density 0.048%

    No Known Activations