© 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. 19723
    Prev
    Next
    INDEX
    Explanations

    phrases related to emphasizing the singular or individual nature of something

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "every single" in relation to 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
    yrinth
    -0.82
    olas
    -0.77
    ÅĤ
    -0.73
    eln
    -0.73
    arium
    -0.70
    ersive
    -0.69
    arty
    -0.67
    icz
    -0.67
    aline
    -0.67
    erves
    -0.65
    POSITIVE LOGITS
    THING
    1.08
     digits
    0.91
     digit
    0.87
     minute
    0.83
     dollar
    0.83
    ONE
    0.76
    meal
    0.75
     person
    0.74
     single
    0.73
    WHERE
    0.72
    Activations Density 0.014%

    No Known Activations