© 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. 6-RES-JB
    11. 9189
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical destruction and injury

    oai_token-act-pair · gpt-3.5-turbo

    words associated with violence and destruction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eq
    -0.68
     href
    -0.66
    cest
    -0.63
     Flavoring
    -0.63
    tein
    -0.63
    rosso
    -0.61
    alone
    -0.59
     phr
    -0.59
    Sol
    -0.58
    argon
    -0.58
    POSITIVE LOGITS
    iHUD
    0.79
    tered
    0.67
     anew
    0.66
    stretched
    0.65
     deteriorated
    0.65
     hinges
    0.65
    aeus
    0.65
    arie
    0.62
     Fargo
    0.60
    hement
    0.59
    Activations Density 0.715%

    No Known Activations