© 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. 3-RES-JB
    11. 15686
    Prev
    Next
    INDEX
    Explanations

    words related to physical tearing or damage

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "torn" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITNESS
    -0.79
    arten
    -0.77
    lain
    -0.76
    racuse
    -0.73
    VERTISEMENT
    -0.72
    aretz
    -0.71
    aminer
    -0.70
    ALT
    -0.70
    VO
    -0.69
    OUNT
    -0.69
    POSITIVE LOGITS
    adoes
    1.55
    ados
    1.05
     torn
    0.93
     parting
    0.86
    adic
    0.85
     earthqu
    0.81
     estranged
    0.80
     exting
    0.77
     unprotected
    0.76
     Torn
    0.75
    Activations Density 0.008%

    No Known Activations