© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 2298
    Prev
    Next
    INDEX
    Explanations

    phrases related to reputation, particularly negative connotations

    oai_token-act-pair · gpt-3.5-turbo

    words associated with reputation and its alterations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dstg
    -0.85
     Incre
    -0.72
    abee
    -0.65
    fill
    -0.64
    bles
    -0.64
    azaki
    -0.63
    anas
    -0.62
    ohm
    -0.61
    anges
    -0.61
    chini
    -0.60
    POSITIVE LOGITS
     reputation
    3.73
     notoriety
    1.85
     renown
    1.68
     credibility
    1.63
     fame
    1.49
     prestige
    1.47
     nickname
    1.46
     popularity
    1.25
     penchant
    1.22
     moniker
    1.20
    Activations Density 0.017%

    No Known Activations