© 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. 18516
    Prev
    Next
    INDEX
    Explanations

    verbs related to discovery, revelation, and exploration

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to taking action or making changes

    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
     reper
    -0.66
     sidx
    -0.64
    Downloadha
    -0.59
    ULTS
    -0.56
     Sina
    -0.55
    RB
    -0.53
     Haram
    -0.53
     tatt
    -0.53
     Âł Âł Âł Âł
    -0.51
     brim
    -0.51
    POSITIVE LOGITS
    ing
    3.21
    ed
    2.05
    ING
    1.93
    ings
    1.70
    ning
    1.60
    edIn
    1.59
    ingly
    1.53
    ership
    1.50
    edly
    1.48
    ers
    1.46
    Activations Density 0.927%

    No Known Activations