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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-RES-JB
    6. 22614
    Prev
    Next
    INDEX
    Explanations

    specific news outlets

    oai_token-act-pair · gpt-3.5-turbo

    references to news publications and alerts

    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
    ierre
    -0.80
    amiya
    -0.78
    ersen
    -0.76
    igham
    -0.73
    ħĭ
    -0.71
    Äĩ
    -0.69
     Oss
    -0.64
    utical
    -0.64
    Gy
    -0.63
    */(
    -0.63
    POSITIVE LOGITS
     Mubarak
    0.69
    zai
    0.69
    clinton
    0.68
     eleph
    0.65
    umbn
    0.64
     Newsp
    0.62
    anamo
    0.62
    Donnell
    0.62
     Leopard
    0.61
     NCT
    0.61
    Activations Density 0.156%

    No Known Activations