© 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. 14082
    Prev
    Next
    INDEX
    Explanations

    words related to senses or sensibility

    oai_token-act-pair · gpt-3.5-turbo

    the term "sense" and its variations, indicating discussions about perceived understanding or awareness

    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
    URN
    -0.74
    raphic
    -0.69
    bearing
    -0.69
     Kessler
    -0.65
     roy
    -0.64
     archived
    -0.64
    ourn
    -0.63
    ICAN
    -0.63
     FML
    -0.63
     Ashton
    -0.62
    POSITIVE LOGITS
     Sense
    1.32
    Sense
    1.06
    sense
    0.91
    ables
    0.86
    edIn
    0.83
    omatic
    0.78
    ibility
    0.77
    iencies
    0.76
    terday
    0.76
    able
    0.73
    Activations Density 0.004%

    No Known Activations