© 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. 4-RES-JB
    11. 6453
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing certainty or clarity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "obviously" in various contexts

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

    No Comments

    Negative Logits
    enced
    -0.81
    board
    -0.74
    insula
    -0.73
    ularity
    -0.72
    lé
    -0.72
    itions
    -0.72
    enta
    -0.72
    vez
    -0.71
    uese
    -0.70
    lite
    -0.69
    POSITIVE LOGITS
    NULL
    0.88
    س
    0.79
     correct
    0.69
     identifiable
    0.67
     parted
    0.66
     misunderstand
    0.65
     deline
    0.64
     inconven
    0.64
     inher
    0.64
    icably
    0.63
    Activations Density 0.018%

    No Known Activations