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. 1-RES-JB
    6. 12409
    Prev
    Next
    INDEX
    Explanations

    words ending in '-ially' with a higher activation value

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that modify or describe characteristics or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    href
    -0.71
    Trend
    -0.68
    ocene
    -0.63
     Chaser
    -0.63
    ilan
    -0.62
     Tribune
    -0.62
     Nor
    -0.62
    uras
    -0.62
     Franks
    -0.62
     Orchestra
    -0.62
    POSITIVE LOGITS
    ially
    1.19
     speaking
    0.91
    mph
    0.76
    inately
    0.74
    ename
    0.71
     educated
    0.71
     avail
    0.70
    quire
    0.70
     extinct
    0.69
    mares
    0.69
    Activations Density 0.005%

    No Known Activations