© 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. 7-RES-JB
    11. 12648
    Prev
    Next
    INDEX
    Explanations

    actions related to aggression or coercion

    oai_token-act-pair · gpt-3.5-turbo

    phrases and concepts related to intimidation and threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.89
    aird
    -0.86
     Volunte
    -0.80
    BuyableInstoreAndOnline
    -0.71
    algia
    -0.67
    ammy
    -0.66
    ItemImage
    -0.66
    venture
    -0.65
    oult
    -0.65
    utenberg
    -0.64
    POSITIVE LOGITS
     unsuspecting
    1.29
     opponents
    1.10
     foes
    1.01
     enemy
    0.97
     offending
    0.94
     opponent
    0.92
     enemies
    0.92
     anyone
    0.91
     adversaries
    0.91
     anybody
    0.87
    Activations Density 0.764%

    No Known Activations