© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18816
    Prev
    Next
    INDEX
    Explanations

    words related to criticism and attack in a political or personal context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to aggressive criticism or negative targeting actions

    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
    artifacts
    -0.72
     heartbeat
    -0.67
    66666666
    -0.66
    ECK
    -0.66
    lycer
    -0.65
    olen
    -0.64
     seams
    -0.62
    hess
    -0.62
    aea
    -0.62
    aple
    -0.61
    POSITIVE LOGITS
     leveled
    1.06
     slander
    0.99
     ridicule
    0.98
     accusing
    0.98
     slurs
    0.97
     vil
    0.96
     smear
    0.95
     dispar
    0.94
     insults
    0.94
     hurled
    0.92
    Activations Density 0.222%

    No Known Activations