© 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. 2-RES-JB
    11. 18365
    Prev
    Next
    INDEX
    Explanations

    words related to discomfort or unease

    oai_token-act-pair · gpt-3.5-turbo

    words that convey feelings of discomfort and unease

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥ³
    -0.82
    ramid
    -0.80
    Interstitial
    -0.77
    INAL
    -0.75
    ãĤ·ãĥ£
    -0.70
    BOOK
    -0.69
    ãĥŁ
    -0.69
    OD
    -0.68
    icle
    -0.68
    archives
    -0.67
    POSITIVE LOGITS
     une
    1.33
     jour
    0.86
    quiet
    0.85
     intrins
    0.79
    qi
    0.78
     discont
    0.77
    igible
    0.76
    arest
    0.76
     scrut
    0.75
     fue
    0.71
    Activations Density 0.009%

    No Known Activations