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. 23441
    Prev
    Next
    INDEX
    Explanations

    phrases or words ending with 'll'

    oai_token-act-pair · gpt-3.5-turbo

    references to characters and their roles in a story

    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
    */(
    -0.77
    EStream
    -0.72
    ¥ŀ
    -0.70
    lished
    -0.70
     guiActiveUn
    -0.66
    uliffe
    -0.66
    cription
    -0.63
    joined
    -0.63
    cade
    -0.63
     stoked
    -0.62
    POSITIVE LOGITS
    oyd
    1.27
    uminati
    1.13
    ounge
    1.13
    ows
    1.02
    iard
    1.00
    sburgh
    0.98
    ength
    0.97
    inois
    0.97
    uci
    0.94
    ibrary
    0.94
    Activations Density 0.026%

    No Known Activations