© 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. 4-RES-JB
    11. 13128
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotional distress or overwhelming feelings

    oai_token-act-pair · gpt-3.5-turbo

    references to emotional distress, particularly crying or tears

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

    No Comments

    Negative Logits
    eers
    -0.73
    ancial
    -0.71
    atar
    -0.69
    ENCY
    -0.69
    eor
    -0.67
    ATA
    -0.64
    avanaugh
    -0.64
    abilities
    -0.64
    herty
    -0.63
    ŃĶ
    -0.63
    POSITIVE LOGITS
    bows
    1.07
    stals
    0.97
    stained
    0.96
     tears
    0.96
    bow
    0.88
     Tears
    0.86
    fters
    0.80
    stal
    0.78
     stained
    0.77
     beads
    0.77
    Activations Density 0.011%

    No Known Activations