© 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. 14699
    Prev
    Next
    INDEX
    Explanations

    phrases related to a situation that continues or persists

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating ongoing or persistent conditions

    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
    -0.94
    DragonMagazine
    -0.72
    Lex
    -0.67
    onica
    -0.65
    PsyNetMessage
    -0.65
    ellar
    -0.64
    isson
    -0.63
    ongyang
    -0.63
     externalToEVAOnly
    -0.62
    DI
    -0.61
    POSITIVE LOGITS
     unchanged
    1.28
     intact
    1.19
     unanswered
    1.14
     untouched
    1.04
     unsolved
    1.03
     undefeated
    1.00
     undecided
    0.95
     unaffected
    0.93
     unresolved
    0.92
     steadfast
    0.91
    Activations Density 0.032%

    No Known Activations