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. 9-RES-JB
    6. 22370
    Prev
    Next
    INDEX
    Explanations

    mentions of specific entities and their attributes

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fortun
    -0.76
     myster
    -0.71
     prolifer
    -0.68
     sacrific
    -0.68
     mathemat
    -0.67
     uranium
    -0.67
     incorpor
    -0.65
     horm
    -0.64
     Mobil
    -0.63
     welcomed
    -0.63
    POSITIVE LOGITS
    ï¸ı
    1.14
    own
    0.97
    sama
    0.85
    _>
    0.85
    iversary
    0.84
    ufact
    0.84
    ï¸
    0.84
    ship
    0.84
    Wilson
    0.80
    s
    0.79
    Activations Density 0.267%

    No Known Activations