© 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. 7-RES-JB
    11. 23080
    Prev
    Next
    INDEX
    Explanations

    phrases associated with providing explanations or justifications

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "the reason" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KY
    -0.74
    chron
    -0.63
     Carbuncle
    -0.61
    rog
    -0.60
     helicop
    -0.60
    inav
    -0.60
    wana
    -0.59
     neighb
    -0.57
    borg
    -0.57
    ALTH
    -0.57
    POSITIVE LOGITS
     why
    1.20
    abl
    1.10
    why
    0.97
     WHY
    0.94
     behind
    0.86
    ably
    0.76
     Why
    0.74
     cited
    0.73
    Why
    0.73
    quickShipAvailable
    0.71
    Activations Density 0.029%

    No Known Activations