© 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. 16116
    Prev
    Next
    INDEX
    Explanations

    adjectives describing personal attributes or moral values

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and descriptors related to personal character and attributes

    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
     hemor
    -0.72
     deteriorating
    -0.64
     pecul
    -0.63
     fracturing
    -0.63
    NetMessage
    -0.62
     vacancy
    -0.61
     Doomsday
    -0.60
    had
    -0.60
    ums
    -0.59
     veins
    -0.59
    POSITIVE LOGITS
     oneself
    1.27
     Yourself
    1.12
     yourself
    1.09
     ourselves
    0.92
     yourselves
    0.90
     forever
    0.82
    parent
    0.76
     myself
    0.75
    uler
    0.75
    igne
    0.74
    Activations Density 0.291%

    No Known Activations