© 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. 11-RES-JB
    11. 9281
    Prev
    Next
    INDEX
    Explanations

    references to taking care of someone or something

    oai_token-act-pair · gpt-3.5-turbo

    references to caregiving and responsibility for others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eele
    -0.59
    ria
    -0.59
    XP
    -0.57
     Klux
    -0.56
    HK
    -0.54
     dyed
    -0.53
    vae
    -0.53
    xxxxxxxx
    -0.52
     Balkans
    -0.52
    -+-+
    -0.50
    POSITIVE LOGITS
    taker
    1.06
     of
    0.91
    worn
    0.86
    taking
    0.77
    free
    0.76
    giving
    0.72
    oles
    0.72
    lessness
    0.71
    ta
    0.70
    orship
    0.70
    Activations Density 0.024%

    No Known Activations