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. 10-RES-JB
    6. 19554
    Prev
    Next
    INDEX
    Explanations

    verbs related to fixing or addressing issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to correction and resolution of issues or problems

    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
    ritical
    -0.71
    quartered
    -0.71
     sidx
    -0.68
    united
    -0.67
    nets
    -0.67
    sol
    -0.66
    ographed
    -0.66
    thood
    -0.65
    bos
    -0.65
    adel
    -0.65
    POSITIVE LOGITS
     discrepancies
    1.29
     misunderstand
    1.27
     deficiencies
    1.26
     inconsistencies
    1.21
     misconceptions
    1.18
     mistakes
    1.18
     shortcomings
    1.15
     grievances
    1.14
     errors
    1.09
     disagreements
    1.09
    Activations Density 0.219%

    No Known Activations