© 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. 8-RES-JB
    11. 20505
    Prev
    Next
    INDEX
    Explanations

    words related to destruction and physical remnants like debris, rubble, and wreckage

    oai_token-act-pair · gpt-3.5-turbo

    references to debris and rubble in the context of destruction or disaster scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Demand
    -0.81
    osexual
    -0.71
    ventus
    -0.71
    priority
    -0.69
    vals
    -0.68
    VPN
    -0.68
    OPA
    -0.67
    cise
    -0.66
    zee
    -0.66
    ndra
    -0.66
    POSITIVE LOGITS
     piles
    1.08
     debris
    1.02
     remnants
    1.02
     fragments
    1.01
     litter
    0.95
     rubble
    0.94
     heap
    0.94
     pile
    0.92
     salv
    0.89
     littered
    0.86
    Activations Density 0.076%

    No Known Activations