© 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. 9-RES-JB
    11. 17897
    Prev
    Next
    INDEX
    Explanations

    words related to negative events or situations, particularly emphasizing the concept of "worst."

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of extreme negativity or adverse conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ynthesis
    -0.87
    sure
    -0.80
    ivating
    -0.77
    uador
    -0.77
    cript
    -0.75
    leans
    -0.74
    trl
    -0.74
    itialized
    -0.72
    arya
    -0.72
    plex
    -0.70
    POSITIVE LOGITS
     offender
    1.11
     offenders
    1.08
     nightmare
    0.99
     nightmares
    0.94
     behaved
    0.86
     imaginable
    0.83
     atrocities
    0.79
     mistake
    0.78
     disasters
    0.78
    Versions
    0.76
    Activations Density 0.054%

    No Known Activations