© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 1637
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for words related to capturing something or someone

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "capture."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heit
    -0.80
     Yug
    -0.74
    rees
    -0.67
    sch
    -0.67
    Whe
    -0.65
    mus
    -0.64
    hers
    -0.64
     Gork
    -0.64
     Yog
    -0.63
    ulty
    -0.63
    POSITIVE LOGITS
     capture
    3.85
     capturing
    2.72
     Capture
    2.65
     captures
    2.53
     captured
    2.24
    Capture
    2.18
    capt
    2.09
     recapt
    2.06
    Capt
    1.51
     capt
    1.34
    Activations Density 0.014%

    No Known Activations