© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 9681
    Prev
    Next
    INDEX
    Explanations

    words related to fire

    oai_token-act-pair · gpt-3.5-turbo

    the presence of words related to fire, combustion, or burning

    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
     shopping
    -0.64
     spo
    -0.62
     Atmosp
    -0.62
     PTS
    -0.60
     Chinatown
    -0.60
     nutrition
    -0.59
     outl
    -0.59
     dumping
    -0.58
     Shant
    -0.57
     chemistry
    -0.57
    POSITIVE LOGITS
    ire
    4.51
    ires
    2.80
    IRE
    2.68
    iring
    2.01
    ired
    2.00
    irement
    1.76
    yre
    1.46
    ir
    1.43
    irable
    1.42
    iration
    1.36
    Activations Density 0.008%

    No Known Activations