© 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. 11-RES-JB
    11. 10076
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism and blame directed at authorities

    oai_token-act-pair · gpt-3.5-turbo

    assertive statements regarding authority and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    requent
    -0.79
    VERTISEMENT
    -0.70
    aughtered
    -0.69
     Moines
    -0.68
    acters
    -0.68
    avascript
    -0.67
    icipated
    -0.67
    Scroll
    -0.67
    izable
    -0.67
    estyles
    -0.66
    POSITIVE LOGITS
     complicit
    1.45
     ignoring
    1.39
     conspiring
    1.38
     hypoc
    1.35
     abusing
    1.32
     waging
    1.30
     undermining
    1.27
     refusing
    1.26
     denying
    1.26
     behaving
    1.25
    Activations Density 0.217%

    No Known Activations