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. 19650
    Prev
    Next
    INDEX
    Explanations

    adjectives expressing intensity or strength

    oai_token-act-pair · gpt-3.5-turbo

    terms related to intensity and characteristics of actions or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    hoff
    -0.67
    sites
    -0.64
     Expend
    -0.64
    appa
    -0.63
    headers
    -0.63
    enegger
    -0.62
    orks
    -0.61
    inate
    -0.61
    Mech
    -0.61
    ilda
    -0.60
    POSITIVE LOGITS
     resembling
    1.19
     reminiscent
    1.16
     comparable
    1.11
     akin
    1.10
     unsu
    1.08
     similar
    1.07
     indistinguishable
    1.06
     unimaginable
    1.06
     unworthy
    1.00
     analogous
    1.00
    Activations Density 0.427%

    No Known Activations