© 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. 8-RES-JB
    11. 8047
    Prev
    Next
    INDEX
    Explanations

    phrases related to designing and building

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the conjunction "and."

    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
    NULL
    -0.76
    nos
    -0.72
    hell
    -0.71
    rice
    -0.71
    ifferent
    -0.70
    yip
    -0.70
    hunt
    -0.69
    ###
    -0.68
     Doors
    -0.68
    nee
    -0.67
    POSITIVE LOGITS
     maintain
    0.93
     nurture
    0.88
     implement
    0.83
     administ
    0.82
     oversaw
    0.82
     manage
    0.81
     maintained
    0.80
     operate
    0.79
     propagate
    0.79
     nurt
    0.76
    Activations Density 0.165%

    No Known Activations