Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 603
    Prev
    Next
    INDEX
    Explanations

    texts related to various topics and subjects, potentially indicating a broad search criterion rather than a specific focus

    oai_token-act-pair · gpt-3.5-turbo

    references to specific articles or topics for discussion

    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
    rities
    -0.72
    Ĭ±
    -0.69
    iors
    -0.67
    ibles
    -0.66
    ãĥı
    -0.66
    drops
    -0.65
    »Ĵ
    -0.64
    Cs
    -0.64
     Temper
    -0.63
    ¶æ
    -0.62
    POSITIVE LOGITS
    ebin
    0.81
     informational
    0.77
    ython
    0.75
     affiliate
    0.75
     crochet
    0.71
     updated
    0.68
     incomplete
    0.68
     POLITICO
    0.68
     bookmark
    0.66
    addle
    0.65
    Activations Density 0.306%

    No Known Activations