© 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. 2-RES-JB
    11. 5881
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Loglis"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Lis" or variations of it in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Immunity
    -0.80
    ¥ŀ
    -0.76
     precinct
    -0.67
     seizure
    -0.65
     consequences
    -0.64
     destinations
    -0.63
     implications
    -0.62
     payoff
    -0.62
     outcomes
    -0.60
     minimized
    -0.59
    POSITIVE LOGITS
    berger
    1.08
    tesy
    1.05
    ãĥ³ãĤ¸
    1.03
    utenant
    1.03
    boa
    1.03
    backer
    0.93
    bor
    0.88
    ierre
    0.85
    earch
    0.85
    cano
    0.84
    Activations Density 0.014%

    No Known Activations