© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    6. 12488
    Prev
    Next
    INDEX
    Explanations

    positive qualities or virtues in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to virtues and qualities, especially in a comparative or evaluative context

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

    No Comments

    Negative Logits
    raid
    -0.72
    rolled
    -0.66
    ©¶æ
    -0.65
    engine
    -0.64
    Mass
    -0.64
    idden
    -0.63
    rolling
    -0.63
    closure
    -0.61
    bone
    -0.60
    DA
    -0.60
    POSITIVE LOGITS
    cape
    0.94
     merits
    0.94
     talents
    0.93
     virtues
    0.85
     merit
    0.80
    pring
    0.79
    uggest
    0.78
    mith
    0.75
     trump
    0.73
    omething
    0.71
    Activations Density 0.042%

    No Known Activations