© 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. 8-RES-JB
    11. 6320
    Prev
    Next
    INDEX
    Explanations

    phrases related to a decision to stay or continue

    oai_token-act-pair · gpt-3.5-turbo

    the term "remain" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.82
    PsyNetMessage
    -0.76
    ologies
    -0.75
     Cosponsors
    -0.70
    ohydrate
    -0.67
    enegger
    -0.67
     Blossom
    -0.66
    è¦ļéĨĴ
    -0.66
    ongyang
    -0.65
    isson
    -0.63
    POSITIVE LOGITS
     unchanged
    1.16
     intact
    1.07
     afloat
    1.01
     silent
    0.99
     steadfast
    0.99
     untouched
    0.93
     unaffected
    0.93
     faithful
    0.92
     stationary
    0.89
     undefeated
    0.89
    Activations Density 0.046%

    No Known Activations