© 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. 5989
    Prev
    Next
    INDEX
    Explanations

    the word "riddle" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "riddle"

    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
    ult
    -0.80
    ultan
    -0.76
    irtual
    -0.73
     Palestin
    -0.73
     srf
    -0.71
    Interstitial
    -0.68
    rities
    -0.67
    dar
    -0.66
    ORK
    -0.65
     Seym
    -0.64
    POSITIVE LOGITS
    iddles
    0.95
    iddle
    0.91
    eering
    0.87
    etr
    0.85
    hyde
    0.83
    glers
    0.81
     Manor
    0.78
    pad
    0.77
    eer
    0.74
     tease
    0.74
    Activations Density 0.009%

    No Known Activations