© 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. 10-RES-JB
    11. 11459
    Prev
    Next
    INDEX
    Explanations

    words related to negativity and adverse effects

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with negative impact or perceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    plain
    -0.93
    ource
    -0.84
    Hide
    -0.84
    ablished
    -0.78
    here
    -0.78
    nington
    -0.77
    racuse
    -0.76
    ruff
    -0.75
    REDACTED
    -0.74
    DOM
    -0.74
    POSITIVE LOGITS
     consequences
    1.21
     impact
    1.15
     impacts
    1.13
     repercussions
    1.12
     publicity
    1.11
     effects
    1.06
     feedback
    1.06
     affect
    1.05
     gearing
    1.05
     stereotypes
    1.05
    Activations Density 0.045%

    No Known Activations