© 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. 0-RES-JB
    11. 8408
    Prev
    Next
    INDEX
    Explanations

    accusatory language, specifically verbs related to blaming or charging someone with wrongdoing

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to accusations and claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adaptations
    -0.72
    ohm
    -0.72
     Essential
    -0.70
     Flex
    -0.68
     mes
    -0.67
     Relax
    -0.67
     functional
    -0.66
     Transition
    -0.64
     Reynolds
    -0.64
     conserv
    -0.63
    POSITIVE LOGITS
     accusing
    2.95
     accuse
    2.92
     accusation
    2.63
     accuses
    2.62
     accusations
    2.34
     accused
    2.14
     accus
    1.97
     accuser
    1.82
     blaming
    1.61
     allegation
    1.52
    Activations Density 0.022%

    No Known Activations