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. 11-RES-JB
    6. 15473
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical equipment or tools

    oai_token-act-pair · gpt-3.5-turbo

    references to various entities and their associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xit
    -0.76
    will
    -0.68
    Will
    -0.65
    osen
    -0.64
    shall
    -0.63
    emonic
    -0.60
     will
    -0.60
    fourth
    -0.60
    Ô
    -0.58
    catentry
    -0.58
    POSITIVE LOGITS
     consisted
    1.70
     resembled
    1.59
     lacked
    1.47
     smelled
    1.47
     seemed
    1.46
     differed
    1.38
     tended
    1.38
     hadn
    1.36
     looked
    1.32
     belonged
    1.31
    Activations Density 0.565%

    No Known Activations