© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1-RES-JB
    11. 9559
    Prev
    Next
    INDEX
    Explanations

    phrases related to selfish behavior

    oai_token-act-pair · gpt-3.5-turbo

    references to selfishness and altruism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.88
    ĸļ
    -0.80
    annis
    -0.79
    STD
    -0.72
    gran
    -0.71
    quart
    -0.71
    acea
    -0.70
     Ibid
    -0.70
    ORN
    -0.68
     Room
    -0.68
    POSITIVE LOGITS
     selfish
    1.11
    istical
    1.08
     altru
    0.99
     minded
    0.88
     greed
    0.88
     motive
    0.85
    istic
    0.83
    rifice
    0.82
     motives
    0.80
    istically
    0.79
    Activations Density 0.012%

    No Known Activations