© 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. 11-RES-JB
    11. 9943
    Prev
    Next
    INDEX
    Explanations

    references to different types of violence and harassment

    oai_token-act-pair · gpt-3.5-turbo

    topics related to violence and harassment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mega
    -0.72
     Slim
    -0.66
    pop
    -0.64
    izons
    -0.63
     outlook
    -0.63
    yssey
    -0.62
     Blueprint
    -0.62
    hedral
    -0.62
    Bright
    -0.61
    Zen
    -0.61
    POSITIVE LOGITS
     perpetrated
    1.30
     inflicted
    1.25
     oneself
    1.04
     punishable
    1.04
     offences
    1.03
     prohibited
    1.02
     unintentional
    1.00
     uttered
    0.99
     inflic
    0.99
     manslaughter
    0.98
    Activations Density 0.338%

    No Known Activations