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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10051
    Prev
    Next
    INDEX
    Explanations

    words related to negative emotions, particularly sadness

    oai_token-act-pair · gpt-3.5-turbo

    expressions and themes related to sadness

    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
    •layer 4 - sadness

    No Comments

    Negative Logits
    ouver
    -0.78
    byter
    -0.68
    RAFT
    -0.68
    cellent
    -0.67
     FANT
    -0.65
    authorized
    -0.65
    orthy
    -0.65
    iltration
    -0.64
     fielded
    -0.64
     guided
    -0.64
    POSITIVE LOGITS
    der
    1.25
    omas
    1.16
    istic
    1.07
    istically
    1.02
    Sad
    0.98
    die
    0.90
     sad
    0.86
    stal
    0.85
    mouth
    0.84
    imaru
    0.82
    Activations Density 0.014%

    No Known Activations