© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 14332
    Prev
    Next
    INDEX
    Explanations

    statements or questions asking for reasons or explanations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "why" indicating inquiries or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roller
    -0.74
    ymph
    -0.71
    ages
    -0.70
    trop
    -0.68
    rop
    -0.66
    robe
    -0.64
    amps
    -0.63
     puck
    -0.63
    field
    -0.62
     Sailor
    -0.62
    POSITIVE LOGITS
    soever
    1.16
     why
    1.14
    why
    1.08
     WHY
    1.01
    iterranean
    0.84
    ihad
    0.83
    Why
    0.82
     exactly
    0.77
    tical
    0.75
    utterstock
    0.74
    Activations Density 0.036%

    No Known Activations