© 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. 22182
    Prev
    Next
    INDEX
    Explanations

    information about picking up or collecting things

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "pick up" and its variations

    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
    parable
    -0.82
     suff
    -0.75
    inguished
    -0.72
     depths
    -0.66
    ctic
    -0.65
    ĨĴ
    -0.64
    perate
    -0.62
     corps
    -0.58
    anto
    -0.58
     Suff
    -0.58
    POSITIVE LOGITS
    shit
    0.82
    illet
    0.69
    react
    0.67
    ubes
    0.66
    WARD
    0.66
    à¹
    0.65
    å§
    0.65
    JV
    0.64
    LOAD
    0.64
    Ban
    0.63
    Activations Density 0.217%

    No Known Activations