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. 15069
    Prev
    Next
    INDEX
    Explanations

    past tense verbs that suggest completion or accomplishment

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "laid" in various contexts

    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
    =-=-=-=-=-=-=-=-
    -0.75
    ities
    -0.74
    externalActionCode
    -0.72
    acca
    -0.69
    ively
    -0.68
    qua
    -0.65
    ernaut
    -0.64
    ivals
    -0.63
    iles
    -0.62
    obs
    -0.62
    POSITIVE LOGITS
    sheets
    0.84
    galitarian
    0.83
     laid
    0.82
     groundwork
    0.81
    ndra
    0.79
    mate
    0.79
    mination
    0.78
     siege
    0.76
    tons
    0.76
    hog
    0.74
    Activations Density 0.013%

    No Known Activations