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. 179
    Prev
    Next
    INDEX
    Explanations

    phrases related to social, political, and technological advancements or changes

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used in lists or connections between concepts

    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
    agle
    -0.75
    atan
    -0.74
    poke
    -0.71
    fur
    -0.70
    lot
    -0.69
    bo
    -0.68
    own
    -0.68
    tale
    -0.68
    ibo
    -0.67
    DX
    -0.67
    POSITIVE LOGITS
     thereby
    1.17
     thus
    1.07
     hence
    1.06
     consequently
    1.03
     thence
    0.90
     assorted
    0.90
     therefore
    0.88
     consequ
    0.86
     possibly
    0.81
     vice
    0.79
    Activations Density 0.587%

    No Known Activations