© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 12062
    Prev
    Next
    INDEX
    Explanations

    words related to financial or economic contexts, specifically related to funding and financial figures

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "che."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eleph
    -0.75
    INGTON
    -0.72
     Archdemon
    -0.71
    ãĥ¼ãĥĨãĤ£
    -0.69
     advoc
    -0.69
     nomine
    -0.64
    DEF
    -0.64
    ãĥ¼ãĥĨ
    -0.64
     stocking
    -0.63
    é¾
    -0.62
    POSITIVE LOGITS
    fter
    1.06
    apeake
    1.02
    lde
    1.02
    eta
    1.02
    arest
    1.00
    tto
    1.00
    chet
    0.98
    tt
    0.97
    lla
    0.96
    tta
    0.96
    Activations Density 0.008%

    No Known Activations