© 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. 1-RES-JB
    11. 10308
    Prev
    Next
    INDEX
    Explanations

    words related to causing harm or negative consequences

    oai_token-act-pair · gpt-3.5-turbo

    mentions of harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ARCH
    -0.70
     liner
    -0.65
     Pione
    -0.64
     handy
    -0.63
    ipel
    -0.63
     Seasons
    -0.60
    ourn
    -0.60
    Jer
    -0.59
    uncture
    -0.59
    arity
    -0.59
    POSITIVE LOGITS
     harm
    1.31
    onies
    1.25
    lessly
    1.20
     harms
    1.06
    lessness
    0.92
     harming
    0.86
     Harm
    0.85
     endanger
    0.83
     harmed
    0.83
    espie
    0.81
    Activations Density 0.008%

    No Known Activations