© 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. 3742
    Prev
    Next
    INDEX
    Explanations

    phrases related to loss and negative outcomes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "lost" and its variations in context

    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
    furt
    -0.81
    heid
    -0.76
    iste
    -0.72
    sis
    -0.70
    £ı
    -0.68
    Cola
    -0.68
    minimum
    -0.66
    optional
    -0.65
    else
    -0.65
    Statement
    -0.65
    POSITIVE LOGITS
     sight
    1.22
     patience
    1.14
     track
    1.07
     faith
    1.06
     consciousness
    1.05
     control
    1.03
     interest
    1.02
     credibility
    1.00
     touch
    0.98
     composure
    0.97
    Activations Density 0.063%

    No Known Activations