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

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 23846
    Prev
    Next
    INDEX
    Explanations

    phrases related to persistence or dominance, specifically looking for the word "prevail" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "prevail" and its variations, indicating a focus on success or dominance in outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zie
    -0.78
    por
    -0.77
    porter
    -0.74
    hod
    -0.69
    gas
    -0.66
    phan
    -0.66
    uddy
    -0.64
    rug
    -0.64
    container
    -0.64
    olog
    -0.62
    POSITIVE LOGITS
     prevail
    1.18
    enance
    1.10
     prevailed
    1.03
     against
    0.79
    nces
    0.78
     prev
    0.77
    acebook
    0.76
    ANCE
    0.72
     Cantor
    0.71
    ĸļ
    0.71
    Activations Density 0.013%

    No Known Activations