© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 4428
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to causing harm or suffering

    oai_token-act-pair · gpt-3.5-turbo

    words related to causing harm or suffering

    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
    runner
    -0.82
    cube
    -0.78
    cius
    -0.77
    wagen
    -0.75
     Ou
    -0.71
    kj
    -0.70
    chrom
    -0.69
     Blackwell
    -0.69
    mom
    -0.68
    zo
    -0.67
    POSITIVE LOGITS
     inflicted
    1.32
     inflict
    1.04
     inflicting
    1.03
     veter
    1.00
     inflic
    0.97
     adolesc
    0.96
    hesda
    0.89
    terness
    0.88
     wounds
    0.86
     eleph
    0.84
    Activations Density 0.012%

    No Known Activations