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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 11841
    Prev
    Next
    INDEX
    Explanations

    mentions of physical violent acts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to violence and abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     renewed
    -0.64
    icter
    -0.62
    cation
    -0.60
     closure
    -0.60
     narrowed
    -0.60
     optimism
    -0.59
     Emerson
    -0.59
     å¤
    -0.58
    Brexit
    -0.58
     acknowled
    -0.58
    POSITIVE LOGITS
     abusing
    2.70
     assaulting
    1.76
     raping
    1.67
     exploiting
    1.51
     harassing
    1.50
     manipulating
    1.40
     murdering
    1.31
     behaving
    1.18
     violating
    1.14
     wielding
    1.08
    Activations Density 0.027%

    No Known Activations