© 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. 9-RES-JB
    11. 18552
    Prev
    Next
    INDEX
    Explanations

    statements indicating a feeling of fatigue or dissatisfaction

    oai_token-act-pair · gpt-3.5-turbo

    expressions of fatigue or frustration

    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
    aughters
    -0.91
    afort
    -0.83
    ledged
    -0.81
    ourage
    -0.77
    obook
    -0.77
    soDeliveryDate
    -0.77
    dinand
    -0.76
    berus
    -0.75
    NK
    -0.73
    NB
    -0.70
    POSITIVE LOGITS
     seeing
    1.27
     hearing
    1.24
     wasting
    1.11
     dealing
    1.06
     waiting
    1.04
     watching
    0.97
     being
    0.96
     banging
    0.95
     having
    0.94
     repeating
    0.92
    Activations Density 0.119%

    No Known Activations