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. 4015
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "the case" in the text

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "that is/was the case" 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
    arus
    -0.82
     livest
    -0.78
    estern
    -0.76
    urses
    -0.75
    ursday
    -0.73
    airs
    -0.72
    dropping
    -0.71
     todd
    -0.70
    etsk
    -0.69
     destro
    -0.67
    POSITIVE LOGITS
    backs
    0.81
    liest
    0.78
    cases
    0.71
     exception
    0.69
    gs
    0.67
     Ruk
    0.66
     scenario
    0.66
     Canaver
    0.64
    rance
    0.62
    pheus
    0.62
    Activations Density 0.020%

    No Known Activations