© 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. 20524
    Prev
    Next
    INDEX
    Explanations

    terms related to emotions and concerns about specific situations or events

    oai_token-act-pair · gpt-3.5-turbo

    sentiments related to excitement and concern

    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
    ournal
    -0.75
     Tycoon
    -0.68
     plagiar
    -0.64
    advant
    -0.64
     miracle
    -0.63
    dule
    -0.62
     Assist
    -0.62
     Inspection
    -0.61
     Deliver
    -0.61
     Chains
    -0.61
    POSITIVE LOGITS
     unfounded
    1.06
     misplaced
    1.03
     stoked
    1.03
     palpable
    1.00
     aroused
    0.99
     tempered
    0.97
     heightened
    0.96
     dissip
    0.94
     simmer
    0.94
     stemmed
    0.94
    Activations Density 0.290%

    No Known Activations