© 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. 1-RES-JB
    11. 914
    Prev
    Next
    INDEX
    Explanations

    words related to the degree or extent of something, especially negative situations or problems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to severity and seriousness of situations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Passage
    -0.70
    rote
    -0.66
    place
    -0.64
     mans
    -0.64
    compan
    -0.63
     passage
    -0.62
     Wik
    -0.61
    uter
    -0.61
     entrances
    -0.61
     tidy
    -0.61
    POSITIVE LOGITS
     seriousness
    1.33
     severity
    1.25
    iness
    0.98
    worthiness
    0.93
     urgency
    0.89
    anguage
    0.85
    ;;;;
    0.79
    channelAvailability
    0.79
    fulness
    0.77
    ailability
    0.74
    Activations Density 0.011%

    No Known Activations