© 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. 8-RES-JB
    11. 4379
    Prev
    Next
    INDEX
    Explanations

    negative or offensive language

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to societal criticism and personal discontent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    displayText
    -0.90
    UMP
    -0.74
    raft
    -0.64
     Immediately
    -0.62
    announced
    -0.62
     Payments
    -0.62
     reopened
    -0.61
     IPM
    -0.61
    LET
    -0.61
    raltar
    -0.60
    POSITIVE LOGITS
     shitty
    0.99
     fucking
    0.92
     goddamn
    0.90
     shit
    0.89
     fuckin
    0.85
     sociop
    0.85
     fucked
    0.83
     patriarchy
    0.81
     kinda
    0.81
     misogyn
    0.80
    Activations Density 1.178%

    No Known Activations