© 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. 0-RES-JB
    6. 23221
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "riddle" or variations like "iddles" and "ierce"

    oai_token-act-pair · gpt-3.5-turbo

    words related to riddles and puzzles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kell
    -0.74
    phas
    -0.72
     padding
    -0.70
    CG
    -0.70
    ucha
    -0.69
     saturation
    -0.68
     floats
    -0.66
     polish
    -0.66
    UX
    -0.65
    opoly
    -0.63
    POSITIVE LOGITS
    iddle
    2.67
    iddles
    1.45
    ridge
    1.21
     retrieve
    1.18
    actory
    1.15
     Hoover
    1.06
    ierce
    1.05
    iddled
    1.05
     retrieving
    1.02
     Yankee
    1.01
    Activations Density 0.053%

    No Known Activations