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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 3720
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences describing physical damage or destruction

    oai_token-act-pair · gpt-3.5-turbo

    references to physical damage or destruction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gency
    -0.80
    Ranked
    -0.77
    hunter
    -0.77
    atography
    -0.77
    atorial
    -0.75
    udic
    -0.71
    alogy
    -0.70
    ayer
    -0.70
    endi
    -0.68
    abet
    -0.68
    POSITIVE LOGITS
     damaged
    0.96
     Fukushima
    0.81
    adoes
    0.77
     salvage
    0.76
     aback
    0.74
     undermin
    0.72
     survivors
    0.72
     damages
    0.71
     Ukrain
    0.70
     weakest
    0.70
    Activations Density 0.027%

    No Known Activations