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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 14304
    Prev
    Next
    INDEX
    Explanations

    words related to the action of 'coping'

    oai_token-act-pair · gpt-3.5-turbo

    words related to actions of coping and managing situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HD
    -0.70
     sac
    -0.63
     elemental
    -0.62
     Isa
    -0.61
     household
    -0.60
     Lemon
    -0.60
     Nerd
    -0.58
     Fry
    -0.57
     stal
    -0.56
     ie
    -0.56
    POSITIVE LOGITS
    oping
    4.62
    oped
    3.11
    opes
    2.18
    opers
    1.96
    ope
    1.96
    opy
    1.64
    ops
    1.64
    OPE
    1.44
    opic
    1.42
    op
    1.40
    Activations Density 0.010%

    No Known Activations