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. 9825
    Prev
    Next
    INDEX
    Explanations

    terms related to development and progress

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "developing."

    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
    zzi
    -0.80
    lua
    -0.74
    que
    -0.72
    wa
    -0.70
    dos
    -0.68
    nea
    -0.67
    clock
    -0.65
    yes
    -0.65
    duty
    -0.65
    tery
    -0.64
    POSITIVE LOGITS
    iates
    0.91
    iating
    0.89
    mental
    0.80
    iated
    0.78
    iator
    0.78
    urally
    0.78
    irtual
    0.77
    ivism
    0.77
    iets
    0.75
    iations
    0.73
    Activations Density 0.038%

    No Known Activations