© 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. 7-RES-JB
    11. 1800
    Prev
    Next
    INDEX
    Explanations

    terms related to destructive events, especially explosions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "explosion."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lege
    -0.83
    nda
    -0.77
    leg
    -0.75
    jud
    -0.75
    iff
    -0.67
    tern
    -0.66
    vag
    -0.64
    stra
    -0.64
    aunder
    -0.63
    abor
    -0.61
    POSITIVE LOGITS
     explosion
    0.97
     furnace
    0.87
     explosions
    0.87
     ignition
    0.84
     detonated
    0.83
     explodes
    0.82
     Explosion
    0.82
    hower
    0.82
     furn
    0.78
     fireball
    0.76
    Activations Density 0.026%

    No Known Activations