© 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. 10-RES-JB
    11. 10050
    Prev
    Next
    INDEX
    Explanations

    adjectives related to negative states or events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical damage or failure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.92
    utra
    -0.76
    advertisement
    -0.74
    ften
    -0.72
    tis
    -0.70
    WithNo
    -0.69
    llers
    -0.69
    quickShipAvailable
    -0.68
    uders
    -0.66
    guided
    -0.66
    POSITIVE LOGITS
    adoes
    1.07
     carc
    0.79
     limbs
    0.77
     ankles
    0.77
     corpse
    0.74
     roof
    0.72
     remnants
    0.72
     kidney
    0.71
     kidneys
    0.71
     storefront
    0.70
    Activations Density 0.149%

    No Known Activations