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. 4089
    Prev
    Next
    INDEX
    Explanations

    terms related to actions or events happening in a business or government context

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to the creation, production, or transformation of entities and situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    SPONSORED
    -0.68
    enter
    -0.64
    zig
    -0.63
    ãĤ¢ãĥ«
    -0.62
    scribe
    -0.61
    CAST
    -0.60
    las
    -0.60
    urai
    -0.60
    bull
    -0.59
    Phys
    -0.59
    POSITIVE LOGITS
     by
    1.21
     aback
    0.99
     BY
    0.83
     By
    0.71
    By
    0.68
     herein
    0.68
    bys
    0.67
     prominently
    0.66
    by
    0.65
     therein
    0.65
    Activations Density 0.418%

    No Known Activations