© 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. 10184
    Prev
    Next
    INDEX
    Explanations

    words related to sudden impactful actions or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "struck" or its variations in various contexts

    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
    ular
    -0.74
    robe
    -0.74
     NR
    -0.65
     Lomb
    -0.64
     integration
    -0.63
     backup
    -0.62
     backups
    -0.61
    Future
    -0.60
    gy
    -0.58
     Kardash
    -0.58
    POSITIVE LOGITS
     struck
    3.74
     strikes
    1.83
     strike
    1.80
     striking
    1.73
     stricken
    1.61
     hit
    1.46
     hammered
    1.44
    strike
    1.34
    Strike
    1.33
     touched
    1.32
    Activations Density 0.007%

    No Known Activations