© 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. 5323
    Prev
    Next
    INDEX
    Explanations

    mentions of news or situations related to someone's death

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms and possessive pronouns, particularly in relation to loss or death

    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
    ernels
    -0.89
    lator
    -0.79
    Downloadha
    -0.79
    ©¶æ¥µ
    -0.78
    £ı
    -0.74
    JB
    -0.73
    ÙIJ
    -0.72
    Newsletter
    -0.72
    anguage
    -0.71
    ©¶æ
    -0.71
    POSITIVE LOGITS
     departure
    1.55
     disappearance
    1.52
     demise
    1.47
     absence
    1.47
     resignation
    1.40
     presence
    1.40
     whereabouts
    1.38
     candidacy
    1.35
     downfall
    1.33
     arrival
    1.33
    Activations Density 0.250%

    No Known Activations