© 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. 2-RES-JB
    11. 1680
    Prev
    Next
    INDEX
    Explanations

    mentions of 「hay」 in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to hay and its significance

    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
    ongyang
    -0.84
    izations
    -0.80
    inyl
    -0.78
    essee
    -0.75
    iferation
    -0.74
    ODUCT
    -0.72
     prosec
    -0.72
    ifice
    -0.69
    ivity
    -0.68
    urally
    -0.67
    POSITIVE LOGITS
    stack
    1.08
     hay
    1.06
    stead
    0.88
    leaf
    0.86
    weed
    0.83
    pots
    0.82
    bridge
    0.82
    wire
    0.82
    wagon
    0.81
    ashi
    0.81
    Activations Density 0.007%

    No Known Activations