© 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. 7-RES-JB
    11. 2045
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative emotions or situations, particularly sadness

    oai_token-act-pair · gpt-3.5-turbo

    expressions of sadness or melancholy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 7 - sadness

    No Comments

    Negative Logits
    ouver
    -0.76
    vernment
    -0.75
    authorized
    -0.69
    UID
    -0.66
    entials
    -0.65
     FANT
    -0.64
    gemony
    -0.63
    eers
    -0.61
     helic
    -0.60
    RAFT
    -0.60
    POSITIVE LOGITS
    omas
    1.40
    der
    1.31
    istic
    1.25
    istically
    1.22
    die
    0.87
    istical
    0.87
    hus
    0.83
    stal
    0.82
    faced
    0.82
    Sad
    0.82
    Activations Density 0.029%

    No Known Activations