© 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. 7445
    Prev
    Next
    INDEX
    Explanations

    the name "iller" at varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals with the surname "Tiller" in contexts related to death or violence

    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
    ðĿ
    -0.80
    estinal
    -0.70
    raised
    -0.67
    aligned
    -0.67
    ¥µ
    -0.67
    Role
    -0.65
    FW
    -0.63
    Gi
    -0.61
    knit
    -0.60
    gain
    -0.58
    POSITIVE LOGITS
    espie
    1.01
    iller
    0.96
    istas
    0.87
    anguage
    0.86
    uminati
    0.84
    aceous
    0.83
    getic
    0.81
    culosis
    0.79
    apter
    0.79
    iens
    0.79
    Activations Density 0.006%

    No Known Activations