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. 12-RES-JB
    6. 17747
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal achievements and recognitions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    mentions of collaborative efforts and support systems in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     counterfe
    -0.70
    amental
    -0.69
    esm
    -0.67
    uyomi
    -0.66
     disastrous
    -0.66
    execute
    -0.64
    ternity
    -0.64
    sis
    -0.63
    killers
    -0.63
     vomiting
    -0.62
    POSITIVE LOGITS
     finally
    0.88
     such
    0.86
     reunited
    0.74
     so
    0.71
    reen
    0.67
     teamed
    0.67
     Ally
    0.66
    Thanks
    0.66
     afforded
    0.65
    itivity
    0.64
    Activations Density 0.384%

    No Known Activations