© 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. 8219
    Prev
    Next
    INDEX
    Explanations

    instances of actions that result in some kind of launch or initiation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "launch" or variations of it in sentences

    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
    enance
    -0.81
    iev
    -0.81
    words
    -0.79
    anism
    -0.79
    agree
    -0.78
    hes
    -0.70
    ache
    -0.69
    ees
    -0.69
    peak
    -0.67
    reads
    -0.67
    POSITIVE LOGITS
     slew
    1.14
     plethora
    1.10
     new
    1.08
     bunch
    1.04
     raft
    1.03
     handful
    1.00
     series
    0.97
     multitude
    0.95
     dozen
    0.94
     variety
    0.92
    Activations Density 0.375%

    No Known Activations