© 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. 7-RES-JB
    11. 23026
    Prev
    Next
    INDEX
    Explanations

    occurrences where someone wishes to remain anonymous

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "remain" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.82
    ongyang
    -0.71
    isson
    -0.68
    DragonMagazine
    -0.66
    PsyNetMessage
    -0.65
     Blossom
    -0.64
    oglobin
    -0.64
    insula
    -0.63
     Relief
    -0.63
    rote
    -0.62
    POSITIVE LOGITS
     unchanged
    1.14
     intact
    0.99
     afloat
    0.98
     undefeated
    0.97
     steadfast
    0.95
     silent
    0.94
     undet
    0.89
     unaffected
    0.89
     unbeaten
    0.85
     undecided
    0.83
    Activations Density 0.040%

    No Known Activations