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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 16824
    Prev
    Next
    INDEX
    Explanations

    pronouns like "anyone," "their," "who" and "that" along with action verbs like "force," "were," "do," and "have."

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and auxiliary verbs indicating existence or participation

    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
    imar
    -0.58
     understandably
    -0.58
     enormously
    -0.56
     now
    -0.54
    APTER
    -0.54
     Trop
    -0.52
     immensely
    -0.51
     Bigfoot
    -0.51
     then
    -0.51
     thanked
    -0.50
    POSITIVE LOGITS
    Else
    1.09
    abouts
    1.03
    depending
    0.83
     equivalent
    0.82
    acle
    0.81
    nam
    0.80
    phans
    0.73
    chard
    0.71
    odox
    0.70
    Downloadha
    0.70
    Activations Density 0.271%

    No Known Activations