© 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. 2-RES-JB
    11. 13454
    Prev
    Next
    INDEX
    Explanations

    instances where the word "which" is followed by a significant phrase or clause

    oai_token-act-pair · gpt-3.5-turbo

    the word "which" in various contexts

    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
    Behind
    -0.74
    let
    -0.70
    athi
    -0.67
    belt
    -0.66
    ben
    -0.65
    grim
    -0.64
    hat
    -0.64
    ³³³³³³³³
    -0.63
    Bas
    -0.63
    FN
    -0.63
    POSITIVE LOGITS
    soever
    1.04
    xual
    0.89
    akespeare
    0.79
     contrasts
    0.79
    ĸļ
    0.73
     resulted
    0.69
     consists
    0.69
    chwitz
    0.68
     oversees
    0.67
     brings
    0.67
    Activations Density 0.157%

    No Known Activations