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. 20008
    Prev
    Next
    INDEX
    Explanations

    words that end with the suffix '-ably' with a focus on those that have high relevance

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that describe capability or manner

    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
    ongyang
    -0.78
    ancial
    -0.72
    itu
    -0.69
    cffff
    -0.68
    icip
    -0.68
    escription
    -0.67
    utenberg
    -0.67
    raltar
    -0.67
    sters
    -0.66
    sonian
    -0.66
    POSITIVE LOGITS
    idis
    0.72
    jured
    0.71
     disposed
    0.71
    ãĤ©
    0.70
    ffe
    0.69
    ãĤ´ãĥ³
    0.65
     foreseeable
    0.65
    âĶĢâĶĢ
    0.64
    gged
    0.63
    \\\\
    0.63
    Activations Density 0.027%

    No Known Activations