© 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. 3-RES-JB
    6. 22817
    Prev
    Next
    INDEX
    Explanations

    words related to destiny or inevitable outcomes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of fate and its implications

    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
    orney
    -0.82
    atchewan
    -0.71
    ainers
    -0.71
    quart
    -0.70
    ONSORED
    -0.67
    arel
    -0.66
    upt
    -0.65
    rored
    -0.64
    ages
    -0.63
    aquin
    -0.62
    POSITIVE LOGITS
     fate
    1.10
    istically
    0.84
    ality
    0.80
    bringer
    0.79
    blow
    0.79
    claw
    0.78
     havoc
    0.78
    stre
    0.76
    uel
    0.75
    lessly
    0.74
    Activations Density 0.011%

    No Known Activations