© 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 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. 3-RES-JB
    11. 4029
    Prev
    Next
    INDEX
    Explanations

    terms related to the identification of perpetrators in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "perpetrator" and related concepts

    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
    psey
    -0.72
    mel
    -0.68
    zl
    -0.68
    ria
    -0.67
    yip
    -0.66
     Plat
    -0.66
    opian
    -0.65
    thur
    -0.64
    ARY
    -0.64
    andel
    -0.63
    POSITIVE LOGITS
     perpetrated
    1.03
     perpetrator
    0.90
     perpetrators
    0.88
     offenders
    0.82
    ãĥ¼ãĥĨãĤ£
    0.81
     offender
    0.80
     abused
    0.80
     abuse
    0.80
     abuser
    0.79
     committed
    0.74
    Activations Density 0.015%

    No Known Activations