© 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. 17600
    Prev
    Next
    INDEX
    Explanations

    words related to causing or preventing harm

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of harm

    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
    ARCH
    -0.70
    KER
    -0.66
     liner
    -0.66
    zsche
    -0.64
    gran
    -0.62
     handy
    -0.61
    kun
    -0.59
    Interview
    -0.59
    ipel
    -0.59
    aten
    -0.57
    POSITIVE LOGITS
    onies
    1.27
    lessly
    1.19
     harm
    1.06
     harms
    0.96
     inflicted
    0.89
    fully
    0.88
    lessness
    0.88
    ful
    0.86
    ingly
    0.81
    fulness
    0.80
    Activations Density 0.018%

    No Known Activations