© 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. 10-RES-JB
    11. 16082
    Prev
    Next
    INDEX
    Explanations

    words related to irreversibility or irreversible actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to irreconcilable or irreversible situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    auri
    -0.68
    DragonMagazine
    -0.68
    anwhile
    -0.65
     eyed
    -0.65
     buckle
    -0.63
    dayName
    -0.62
    GD
    -0.61
    yrinth
    -0.61
    è¦ļéĨĴ
    -0.60
     Dunk
    -0.60
    POSITIVE LOGITS
    voc
    1.70
    parable
    1.40
    vers
    1.27
    cover
    1.22
    medi
    1.13
    ve
    1.08
    lev
    1.08
    place
    1.08
    par
    1.03
    versible
    1.02
    Activations Density 0.016%

    No Known Activations