© 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. 8-RES-JB
    11. 20193
    Prev
    Next
    INDEX
    Explanations

    phrases related to undermining or weakening something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "undermine" and its forms in various contexts

    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
    lov
    -0.74
    area
    -0.71
    andro
    -0.66
    cise
    -0.65
    onna
    -0.64
    mad
    -0.64
    sa
    -0.61
    onz
    -0.60
    ather
    -0.59
    phe
    -0.59
    POSITIVE LOGITS
     morale
    0.90
     havoc
    0.89
     perceptions
    0.82
     expectations
    0.81
     confidence
    0.80
     livelihood
    0.79
     attempts
    0.73
     credibility
    0.72
     democratically
    0.72
     deterrence
    0.71
    Activations Density 0.083%

    No Known Activations