© 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. 2-RES-JB
    11. 21910
    Prev
    Next
    INDEX
    Explanations

    ambiguous statements that can be interpreted in multiple ways

    oai_token-act-pair · gpt-3.5-turbo

    the adverb "undoubtedly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nan
    -0.78
    gencies
    -0.74
    chens
    -0.71
    len
    -0.71
    rams
    -0.66
    elling
    -0.65
    ockets
    -0.65
    eller
    -0.64
    ublic
    -0.63
    azine
    -0.63
    POSITIVE LOGITS
    ãĥ´ãĤ¡
    0.78
     conclud
    0.74
    Berry
    0.73
     disappoint
    0.72
    theless
    0.71
     benefited
    0.71
     defic
    0.69
     enthusi
    0.68
     detract
    0.67
    è¯
    0.67
    Activations Density 0.009%

    No Known Activations