© 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. 6-RES-JB
    11. 13838
    Prev
    Next
    INDEX
    Explanations

    requests or invitations

    oai_token-act-pair · gpt-3.5-turbo

    phrases and expressions related to permissions and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     meanwhile
    -0.51
    Shar
    -0.51
     Malaysia
    -0.51
     Malays
    -0.50
     Lion
    -0.49
    fin
    -0.49
     Britain
    -0.48
     Malaysian
    -0.47
     Qatar
    -0.47
     Canad
    -0.47
    POSITIVE LOGITS
    pmwiki
    0.61
    ãĥĩãĤ£
    0.59
    etheless
    0.59
    ãĤ¦ãĤ¹
    0.59
    ptin
    0.54
     temptation
    0.54
    morrow
    0.52
    ãģ®
    0.51
    âĵĺ
    0.51
    pas
    0.50
    Activations Density 1.277%

    No Known Activations