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

    Neuronpedia

    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. 3-RES-JB
    11. 437
    Prev
    Next
    INDEX
    Explanations

    phrases discussing the likelihood or ability to succeed in a particular endeavor

    oai_token-act-pair · gpt-3.5-turbo

    the word "it," often in the context of making something happen or achieving an outcome

    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
    anwhile
    -0.76
     Pigs
    -0.65
     distances
    -0.56
     surrounds
    -0.56
    OPLE
    -0.56
    arna
    -0.55
     provided
    -0.54
     setbacks
    -0.54
     keyboards
    -0.54
     underwent
    -0.54
    POSITIVE LOGITS
    Wan
    0.86
    sense
    0.75
     impression
    0.72
    undo
    0.70
    undle
    0.69
    kish
    0.68
    sound
    0.67
     richer
    0.66
     mistake
    0.65
    Ò
    0.65
    Activations Density 0.345%

    No Known Activations