© 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. 8-RES-JB
    11. 3826
    Prev
    Next
    INDEX
    Explanations

    phrases related to enhancing or improving something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to enhancing enjoyment or creating a positive atmosphere

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çīĪ
    -0.55
     renamed
    -0.53
     Romero
    -0.53
    代
    -0.53
    National
    -0.53
    ONSORED
    -0.53
    chnology
    -0.51
     presided
    -0.51
    numbered
    -0.50
     Lange
    -0.50
    POSITIVE LOGITS
     wearer
    0.75
     unwanted
    0.70
     Flavoring
    0.63
     user
    0.63
     pores
    0.61
     functionality
    0.56
     users
    0.55
    llular
    0.55
     Xperia
    0.55
     undesirable
    0.55
    Activations Density 1.209%

    No Known Activations