© 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. 0-RES-JB
    11. 14734
    Prev
    Next
    INDEX
    Explanations

    adjectives related to mental states or behaviors that suggest distress or dysfunction

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mental disturbance or distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omics
    -0.74
     champions
    -0.72
     jersey
    -0.69
     confidently
    -0.68
    CI
    -0.68
    brand
    -0.67
     Camel
    -0.67
     GET
    -0.67
    ilot
    -0.66
     sprint
    -0.65
    POSITIVE LOGITS
     disturbed
    2.95
     disturbing
    2.62
     disturb
    2.44
     disturbance
    2.23
     distur
    1.80
     disturbances
    1.71
     troubling
    1.51
     unsettling
    1.48
    urbed
    1.29
     troubled
    1.29
    Activations Density 0.033%

    No Known Activations