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. 2-RES-JB
    6. 9716
    Prev
    Next
    INDEX
    Explanations

    blends of consonants and vowels, often ending with the letter "k" and a number from 1 to 10 preceding it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ck"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    senal
    -0.90
     Palestin
    -0.89
     exha
    -0.88
     behavi
    -0.82
     livest
    -0.80
     pestic
    -0.80
    accompan
    -0.78
     tradem
    -0.76
     streng
    -0.76
     tremend
    -0.75
    POSITIVE LOGITS
    lace
    1.10
    enstein
    1.03
    patrick
    1.02
    etts
    0.99
    enger
    0.97
    hoff
    0.97
    oning
    0.96
    enberg
    0.92
    lement
    0.92
    ull
    0.92
    Activations Density 0.010%

    No Known Activations