© 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 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. 3-RES-JB
    11. 24140
    Prev
    Next
    INDEX
    Explanations

    phrases expressing regret or sorrow

    oai_token-act-pair · gpt-3.5-turbo

    expressions of regret or sadness about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 3 - sadness

    No Comments

    Negative Logits
    ammy
    -0.91
    ramid
    -0.83
    urat
    -0.77
    NetMessage
    -0.77
    ahon
    -0.76
    smoking
    -0.72
    chn
    -0.71
    ioch
    -0.69
    onz
    -0.69
    cius
    -0.68
    POSITIVE LOGITS
     lament
    0.91
     lamented
    0.82
    ably
    0.79
    anty
    0.77
     mourn
    0.74
    ries
    0.72
     bitterly
    0.69
     aloud
    0.68
    wart
    0.67
    aste
    0.67
    Activations Density 0.025%

    No Known Activations