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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 18193
    Prev
    Next
    INDEX
    Explanations

    powerful verbs related to various types of efforts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to efforts, actions, or measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endment
    -0.61
     olds
    -0.58
    ILE
    -0.58
    Eva
    -0.57
    ocracy
    -0.55
    purpose
    -0.55
    ipes
    -0.53
    WARD
    -0.53
    plet
    -0.53
    votes
    -0.52
    POSITIVE LOGITS
     abound
    1.26
     vary
    1.10
     arose
    1.06
     ensued
    1.02
     sprang
    0.96
     are
    0.96
     flowed
    0.95
     differ
    0.95
     emerged
    0.93
     prevailed
    0.92
    Activations Density 0.298%

    No Known Activations