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. 7958
    Prev
    Next
    INDEX
    Explanations

    words related to legal or official matters

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a connection or relevance to various subjects

    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
    ifter
    -0.81
    âķIJ
    -0.78
    aneers
    -0.73
     Muller
    -0.73
    imates
    -0.69
    UGE
    -0.69
    ardless
    -0.68
    arer
    -0.67
     Trees
    -0.67
    âķIJâķIJ
    -0.66
    POSITIVE LOGITS
     thereto
    0.92
     ancest
    0.88
    worldly
    0.86
    paren
    0.79
     unrelated
    0.77
    lly
    0.77
    ness
    0.77
     reconc
    0.74
    rums
    0.73
    ciplinary
    0.73
    Activations Density 0.018%

    No Known Activations