© 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
    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. 9234
    Prev
    Next
    INDEX
    Explanations

    the word "why"

    oai_token-act-pair · gpt-3.5-turbo

    the word "why" and its variations, indicating a focus on questions or explanations

    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
     Roller
    -0.78
    ymph
    -0.72
    trop
    -0.66
    rop
    -0.66
    amps
    -0.66
    robe
    -0.63
    hern
    -0.62
    lator
    -0.62
     puck
    -0.61
    Zone
    -0.61
    POSITIVE LOGITS
     why
    1.04
    soever
    1.03
     WHY
    0.96
    why
    0.95
    iterranean
    0.80
     exactly
    0.79
    Why
    0.79
    ihad
    0.75
    icago
    0.72
    ricanes
    0.69
    Activations Density 0.034%

    No Known Activations