© 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. 736
    Prev
    Next
    INDEX
    Explanations

    instances where something is excessive or surpasses a certain level

    oai_token-act-pair · gpt-3.5-turbo

    the word "over" in various contexts

    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
    illary
    -0.88
    KE
    -0.69
     partName
    -0.65
     Lauder
    -0.63
    UE
    -0.63
    arium
    -0.63
    Os
    -0.62
    ï¸
    -0.61
    Ô
    -0.61
    ZE
    -0.60
    POSITIVE LOGITS
    tones
    0.93
    lord
    0.93
    loading
    0.91
    drive
    0.90
    haul
    0.89
    priced
    0.84
    hang
    0.83
    ensibly
    0.83
    clock
    0.83
    elin
    0.81
    Activations Density 0.077%

    No Known Activations