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. 22202
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events involving harm or control by others

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "in the hands of."

    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
     redes
    -0.70
    Ann
    -0.69
    andum
    -0.67
    nces
    -0.64
     shaved
    -0.64
    icut
    -0.63
     compr
    -0.62
     hereby
    -0.62
     Maple
    -0.61
    ollo
    -0.61
    POSITIVE LOGITS
    lopp
    0.75
    FUL
    0.69
    mination
    0.68
     Gul
    0.68
    ulator
    0.65
    imately
    0.64
    adle
    0.63
    Storm
    0.62
    ible
    0.59
    innacle
    0.59
    Activations Density 0.053%

    No Known Activations