© 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 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. 0-RES-JB
    11. 12407
    Prev
    Next
    INDEX
    Explanations

    positive and negative descriptors related to personality traits

    oai_token-act-pair · gpt-3.5-turbo

    words related to emotional warmth and playfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IPS
    -0.84
    sed
    -0.78
    ayer
    -0.69
    omed
    -0.68
     Surviv
    -0.67
    Downloadha
    -0.67
    ayers
    -0.66
     mates
    -0.66
     DRAG
    -0.65
     differe
    -0.65
    POSITIVE LOGITS
     playable
    2.19
    hearted
    1.83
     Goodman
    1.46
    heartedly
    1.05
     usable
    1.00
     unre
    0.98
     sculpture
    0.96
    Requ
    0.93
     Requ
    0.88
     Impro
    0.85
    Activations Density 0.031%

    No Known Activations