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. 4-RES-JB
    6. 5150
    Prev
    Next
    INDEX
    Explanations

    words related to honing skills or abilities

    oai_token-act-pair · gpt-3.5-turbo

    words related to "honors" and "honing" skills or abilities

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

    No Comments

    Negative Logits
    TPS
    -0.85
    backer
    -0.76
     Sack
    -0.75
     Esc
    -0.72
    mia
    -0.71
     Axis
    -0.71
    BOOK
    -0.69
     Reaction
    -0.69
     Forth
    -0.69
    Else
    -0.66
    POSITIVE LOGITS
    olulu
    1.14
     hon
    1.05
    ours
    0.96
    rie
    0.89
    animous
    0.88
    ision
    0.86
    ittance
    0.86
    ateurs
    0.85
    esty
    0.83
    ouri
    0.81
    Activations Density 0.009%

    No Known Activations