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. 24219
    Prev
    Next
    INDEX
    Explanations

    adjectives related to weakening or reducing something

    oai_token-act-pair · gpt-3.5-turbo

    words related to reducing or hindering something

    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
     boldly
    -0.68
     prow
    -0.63
     americ
    -0.60
     beware
    -0.59
     wisely
    -0.59
     eyed
    -0.58
     wont
    -0.57
     snail
    -0.57
     Scand
    -0.57
     Brit
    -0.57
    POSITIVE LOGITS
    uate
    0.94
    uates
    0.87
    utive
    0.82
    Increase
    0.81
    activate
    0.79
    chieve
    0.78
    ior
    0.75
    uating
    0.75
    ependent
    0.74
    uce
    0.73
    Activations Density 0.091%

    No Known Activations