Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 20322
    Prev
    Next
    INDEX
    Explanations

    words related to physical damage

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to destruction or physical damage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ranked
    -0.83
    imum
    -0.80
    endi
    -0.73
    gency
    -0.73
    otten
    -0.70
    ayer
    -0.68
    travel
    -0.68
    OPA
    -0.68
    udic
    -0.68
     Pinball
    -0.67
    POSITIVE LOGITS
     damaged
    0.81
     badly
    0.81
    adoes
    0.80
     debris
    0.77
     dere
    0.74
     wreckage
    0.74
     Ukrain
    0.71
     Parts
    0.69
     charred
    0.68
     chunks
    0.67
    Activations Density 0.057%

    No Known Activations