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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 12063
    Prev
    Next
    INDEX
    Explanations

    references to the name "Den" with different variations such as "Denzel", "Denham", and "Denison"

    oai_token-act-pair · gpt-3.5-turbo

    the word "Den" and its variations throughout the text

    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
     behav
    -0.68
    raltar
    -0.68
    EED
    -0.65
    mph
    -0.62
     Jav
    -0.62
    OTH
    -0.62
    é¾įå¥ij士
    -0.62
     ABE
    -0.62
    committee
    -0.60
     Typh
    -0.59
    POSITIVE LOGITS
    omin
    1.13
    omination
    1.12
    zel
    1.06
    izens
    1.03
    izen
    1.02
    wart
    0.93
    itus
    0.93
    emark
    0.90
    ving
    0.90
    unciation
    0.89
    Activations Density 0.009%

    No Known Activations