© 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. 4-RES-JB
    11. 6927
    Prev
    Next
    INDEX
    Explanations

    adjective-noun pairs preceded by "such as"

    oai_token-act-pair · gpt-3.5-turbo

    references to examples or instances of various categories or types

    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
    ertodd
    -0.77
    rition
    -0.76
    itudinal
    -0.73
    emonic
    -0.71
    iliate
    -0.68
    aughs
    -0.64
    olate
    -0.64
    ribution
    -0.62
    uckland
    -0.62
    eless
    -0.62
    POSITIVE LOGITS
    ties
    0.74
    should
    0.72
    parts
    0.71
    cond
    0.71
    things
    0.69
    such
    0.68
    requ
    0.64
     minded
    0.63
    above
    0.62
     prec
    0.61
    Activations Density 0.040%

    No Known Activations