© 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. 6-RES-JB
    11. 1690
    Prev
    Next
    INDEX
    Explanations

    words related to loss or negative events

    oai_token-act-pair · gpt-3.5-turbo

    instances of loss or the word "lost" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sis
    -0.73
    osi
    -0.68
    gon
    -0.66
    mens
    -0.65
    onomic
    -0.62
     Janeiro
    -0.61
    oin
    -0.60
    heid
    -0.60
     primed
    -0.59
    agher
    -0.59
    POSITIVE LOGITS
    luster
    0.80
     miser
    0.74
     aversion
    0.72
     souls
    0.70
     sight
    0.70
    ittens
    0.69
    bite
    0.68
    touch
    0.68
    esses
    0.67
    itive
    0.67
    Activations Density 0.032%

    No Known Activations