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. 3-RES-JB
    6. 14200
    Prev
    Next
    INDEX
    Explanations

    occurrences where the phrase "so far" is used

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating progress or status up to a certain point in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onut
    -0.79
    ycle
    -0.75
    ovo
    -0.73
    olor
    -0.73
    yre
    -0.73
    tap
    -0.72
    psey
    -0.68
    effic
    -0.68
    root
    -0.67
    uala
    -0.67
    POSITIVE LOGITS
    thing
    0.79
    fetched
    0.78
     ahead
    0.75
     awa
    0.73
     away
    0.71
    ghan
    0.69
     exceeds
    0.69
     beyond
    0.68
     elapsed
    0.67
    Ùĩ
    0.67
    Activations Density 0.014%

    No Known Activations