Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9148
    Prev
    Next
    INDEX
    Explanations

    people's names ending in 'lan'

    oai_token-act-pair · gpt-3.5-turbo

    the term "lan" in various contexts, likely related to names or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     STATS
    -0.67
    FACE
    -0.64
    nces
    -0.63
    é¾įå¥ij士
    -0.62
     Britann
    -0.61
     Crunch
    -0.60
     Imm
    -0.58
     Disclosure
    -0.57
    race
    -0.57
     Serious
    -0.56
    POSITIVE LOGITS
    auer
    1.13
    ning
    1.07
    ifest
    1.07
    ovo
    1.02
    unci
    0.98
    ergic
    0.97
    owski
    0.95
    tern
    0.92
    esthetic
    0.92
    imir
    0.91
    Activations Density 0.012%

    No Known Activations