© 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. 15712
    Prev
    Next
    INDEX
    Explanations

    references to criminal acts or instances where harm is inflicted

    oai_token-act-pair · gpt-3.5-turbo

    terms related to aggravated assault and similar crimes

    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
    eth
    -0.79
    hers
    -0.73
    pieces
    -0.70
    ew
    -0.70
    stars
    -0.67
     Techn
    -0.66
    eem
    -0.66
    ees
    -0.63
    shift
    -0.62
    Maker
    -0.62
    POSITIVE LOGITS
     aggravated
    3.57
     aggrav
    1.68
     irritated
    1.17
     exacerbated
    1.12
     compounded
    1.06
     involuntary
    1.04
     indecent
    1.01
     forc
    1.00
     annoyed
    0.99
     agitated
    0.99
    Activations Density 0.015%

    No Known Activations