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. 18530
    Prev
    Next
    INDEX
    Explanations

    image toggle captions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "toggle."

    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
    metic
    -0.71
    esses
    -0.70
    eday
    -0.68
    dates
    -0.67
    umped
    -0.67
    bats
    -0.67
    dating
    -0.67
    ĪĴ
    -0.66
    umble
    -0.63
    umping
    -0.63
    POSITIVE LOGITS
     toggle
    1.12
     caption
    0.93
     "$:/
    0.75
    taboola
    0.74
    Pinterest
    0.72
    Enlarge
    0.66
     Courtesy
    0.65
     autop
    0.64
     clicking
    0.64
     WATCHED
    0.64
    Activations Density 0.005%

    No Known Activations