© 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. 3989
    Prev
    Next
    INDEX
    Explanations

    references to the word "harm"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to harm and its variations

    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
    cers
    -0.67
    issance
    -0.66
     clos
    -0.66
     McGr
    -0.65
    cé
    -0.64
     Cain
    -0.63
     bapt
    -0.63
     Rafael
    -0.62
     rushes
    -0.62
    VEN
    -0.61
    POSITIVE LOGITS
    onics
    1.24
    ony
    1.22
    harm
    1.12
    onic
    1.00
    onia
    1.00
    ropy
    1.00
    onica
    0.98
    oral
    0.92
    onies
    0.85
    ory
    0.83
    Activations Density 0.012%

    No Known Activations