© 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. 4371
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict, criticism, or controversy

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate various forms of attacks or assaults on rights and freedoms

    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
     Nicholson
    -0.66
     involved
    -0.63
     Zup
    -0.63
     Mub
    -0.61
    abases
    -0.61
    vo
    -0.60
    croft
    -0.59
     CCTV
    -0.59
     Moody
    -0.59
    rament
    -0.59
    POSITIVE LOGITS
     sorts
    0.78
    Interstitial
    0.77
     disguise
    0.73
    ãĥĺ
    0.72
     empowerment
    0.70
    enfranch
    0.68
     desperation
    0.68
    geries
    0.68
     oneself
    0.68
     ignorance
    0.67
    Activations Density 0.313%

    No Known Activations