Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 20750
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal cases and disputes

    oai_token-act-pair · gpt-3.5-turbo

    proper names and specific entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     captcha
    -0.59
     Winc
    -0.57
    Nev
    -0.56
    isconsin
    -0.55
    Haw
    -0.54
     consistent
    -0.53
    Tes
    -0.53
     NRL
    -0.53
     Tenn
    -0.53
     Scots
    -0.52
    POSITIVE LOGITS
    rite
    0.76
     consisted
    0.74
     itself
    0.69
     smelled
    0.68
     alone
    0.66
    arently
    0.65
     reportedly
    0.64
    orem
    0.63
     consists
    0.63
    hetically
    0.62
    Activations Density 0.542%

    No Known Activations