© 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. 10-RES-JB
    11. 21477
    Prev
    Next
    INDEX
    Explanations

    personal reflections or thoughts expressed in the first person

    oai_token-act-pair · gpt-3.5-turbo

    personal experiences and expressions of sentiment

    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
     WTC
    -0.66
     Cheong
    -0.65
    uments
    -0.64
    engu
    -0.62
     Robots
    -0.62
     Leopard
    -0.61
     Emails
    -0.60
    amaz
    -0.60
    éļ
    -0.59
    Rank
    -0.59
    POSITIVE LOGITS
     sorely
    1.06
     dreamed
    0.93
     dearly
    0.88
     aspire
    0.84
     regretted
    0.84
     cherished
    0.79
     gladly
    0.78
     nightmares
    0.78
     hotly
    0.78
     vehemently
    0.77
    Activations Density 0.147%

    No Known Activations