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. 10-RES-JB
    6. 4133
    Prev
    Next
    INDEX
    Explanations

    specific terms related to allegations

    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
     Cage
    -0.67
    knife
    -0.65
     grace
    -0.64
     ashore
    -0.63
     sperm
    -0.63
     surve
    -0.62
     Ferry
    -0.62
     $$
    -0.61
     stra
    -0.60
     Wilde
    -0.60
    POSITIVE LOGITS
    edly
    1.62
    orical
    1.38
    ations
    1.36
    heny
    1.33
    orial
    1.30
    ory
    1.18
    iance
    1.12
    rett
    1.11
    atory
    1.08
    orship
    1.02
    Activations Density 0.055%

    No Known Activations