© 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. 20218
    Prev
    Next
    INDEX
    Explanations

    terms related to making things worse by adding to existing problems or difficulties

    oai_token-act-pair · gpt-3.5-turbo

    terms related to worsening or escalating situations

    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
    leans
    -0.81
    inates
    -0.79
    aviour
    -0.77
    avior
    -0.72
    ocene
    -0.72
    pha
    -0.71
    lean
    -0.71
    atical
    -0.70
    atics
    -0.70
    bors
    -0.67
    POSITIVE LOGITS
     suspicions
    1.11
     tensions
    0.98
     havoc
    0.98
     resentment
    0.96
     frustration
    0.95
     misery
    0.95
     animosity
    0.92
     mistrust
    0.90
     frustrations
    0.88
     insecurity
    0.87
    Activations Density 0.185%

    No Known Activations