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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 20807
    Prev
    Next
    INDEX
    Explanations

    words related to violence and harmful actions towards others

    oai_token-act-pair · gpt-3.5-turbo

    terms related to police brutality and cruelty in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocular
    -0.78
    yll
    -0.76
    travel
    -0.74
    amina
    -0.74
    nav
    -0.70
    joining
    -0.70
    agall
    -0.69
    eor
    -0.69
    noon
    -0.69
    aran
    -0.68
    POSITIVE LOGITS
     brutality
    1.13
     abuses
    0.74
     inflicted
    0.74
     cruelty
    0.74
     violence
    0.72
     guiActiveUn
    0.69
    ocity
    0.68
     perpetrated
    0.67
     ridden
    0.67
     oppression
    0.66
    Activations Density 0.008%

    No Known Activations