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. 10-RES-JB
    6. 10940
    Prev
    Next
    INDEX
    Explanations

    adjectives and other words that express strong emotions or opinions

    oai_token-act-pair · gpt-3.5-turbo

    intensely emotional or descriptive language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    helm
    -0.76
    cellence
    -0.73
    ecause
    -0.73
    ievers
    -0.72
    someone
    -0.72
    uph
    -0.71
    orks
    -0.71
    vier
    -0.70
     Exactly
    -0.69
    ©¶æ
    -0.69
    POSITIVE LOGITS
     inability
    1.11
     creations
    1.10
     counterparts
    1.10
     foray
    1.10
     penchant
    1.09
     selves
    1.08
     predecessors
    1.06
     antics
    1.05
     arsenal
    1.04
     namesake
    1.02
    Activations Density 0.241%

    No Known Activations