© 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. 9-RES-JB
    11. 7399
    Prev
    Next
    INDEX
    Explanations

    words related to performing well or achieving success

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to making good use or having fun

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hov
    -0.63
     cracked
    -0.60
    isma
    -0.57
    anwhile
    -0.57
     privately
    -0.56
     nailed
    -0.56
    hens
    -0.55
     approved
    -0.55
    ridor
    -0.54
     Niet
    -0.54
    POSITIVE LOGITS
    roads
    0.82
    ends
    0.80
    sense
    0.77
    fell
    0.74
     mockery
    0.72
     noises
    0.69
     landfall
    0.68
    URE
    0.67
    nell
    0.67
     sacrifices
    0.67
    Activations Density 0.094%

    No Known Activations