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. 1-RES-JB
    6. 9337
    Prev
    Next
    INDEX
    Explanations

    words related to torment or suffering

    oai_token-act-pair · gpt-3.5-turbo

    terms related to torment or suffering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Consent
    -0.71
    ACTED
    -0.69
    Companies
    -0.66
    PRES
    -0.65
    WER
    -0.65
    ortium
    -0.63
    Too
    -0.63
    acebook
    -0.62
    enegger
    -0.62
     Objective
    -0.62
    POSITIVE LOGITS
     tor
    1.11
    onto
    0.87
    vell
    0.82
    ching
    0.81
     moth
    0.80
     wrench
    0.78
    ving
    0.76
    onite
    0.74
    ape
    0.73
    phis
    0.72
    Activations Density 0.009%

    No Known Activations