© 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. 9-RES-JB
    11. 19386
    Prev
    Next
    INDEX
    Explanations

    words related to deep emotions or psychological states

    oai_token-act-pair · gpt-3.5-turbo

    references to deep or intense emotions and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kees
    -0.83
    sites
    -0.82
    arthed
    -0.82
    代
    -0.80
    itures
    -0.78
    neau
    -0.77
    cade
    -0.77
    batch
    -0.76
    oother
    -0.73
    lead
    -0.71
    POSITIVE LOGITS
     desire
    1.73
     resentment
    1.60
     frustration
    1.60
     feelings
    1.52
     hatred
    1.51
     dissatisfaction
    1.50
     frustrations
    1.50
     belief
    1.50
     anger
    1.48
     longing
    1.47
    Activations Density 0.546%

    No Known Activations