© 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. 409
    Prev
    Next
    INDEX
    Explanations

    the word "Edition" following various descriptors

    oai_token-act-pair · gpt-4-turbo

    phrases related to editions or versions of something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Edition" and its variants

    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
    aina
    -0.71
    irling
    -0.67
    thy
    -0.65
    pload
    -0.64
    osh
    -0.64
    ayers
    -0.63
    vati
    -0.63
    ahon
    -0.63
    asonic
    -0.62
    aved
    -0.60
    POSITIVE LOGITS
     Edition
    0.98
    Corp
    0.78
    edition
    0.77
    BSD
    0.70
     Reborn
    0.70
    ARCH
    0.67
    wards
    0.67
    Choice
    0.63
     edition
    0.62
    ctl
    0.62
    Activations Density 0.007%

    No Known Activations