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. 19893
    Prev
    Next
    INDEX
    Explanations

    people's names followed by arbitrary strings of characters

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names related to specific individuals, organizations, and locations

    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
     NRL
    -0.70
    aukee
    -0.64
     Corpus
    -0.61
    Tes
    -0.59
    ishable
    -0.57
    PDATE
    -0.55
    ween
    -0.54
     SPL
    -0.54
    Repeat
    -0.54
     Burg
    -0.53
    POSITIVE LOGITS
     consisted
    0.99
     specializes
    0.97
     reportedly
    0.88
     consists
    0.82
     owns
    0.82
     denies
    0.79
     belonged
    0.78
     died
    0.76
     represents
    0.76
     subsequently
    0.75
    Activations Density 0.506%

    No Known Activations