© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 3363
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical sensations and emotions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of empathy and emotional experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     condu
    -0.73
     Preferences
    -0.68
     accordingly
    -0.67
    enthal
    -0.65
     criteria
    -0.65
     objectionable
    -0.65
    Austral
    -0.65
    arten
    -0.64
     defic
    -0.64
    Topic
    -0.64
    POSITIVE LOGITS
     witnessing
    0.93
     numb
    0.90
     flashbacks
    0.85
     remembering
    0.84
     watching
    0.80
     waking
    0.79
     knowing
    0.78
     hearing
    0.76
     surrounded
    0.76
     imagining
    0.76
    Activations Density 0.590%

    No Known Activations