© 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. 16978
    Prev
    Next
    INDEX
    Explanations

    words related to authority, control, and actions taken by specific individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    active verbs associated with actions or states of being involving characters

    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
    ð
    -0.67
    imum
    -0.66
    Enlarge
    -0.64
     guiActiveUnfocused
    -0.64
    communication
    -0.63
     Modified
    -0.62
    avorable
    -0.62
    Side
    -0.60
     PsyNet
    -0.58
    bush
    -0.57
    POSITIVE LOGITS
     moreover
    1.33
     furthermore
    1.28
     also
    1.16
     therefore
    1.03
     however
    0.91
     meanwhile
    0.90
     certainly
    0.81
     literally
    0.80
     even
    0.77
     doubtless
    0.75
    Activations Density 0.446%

    No Known Activations