© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3623
    Prev
    Next
    INDEX
    Explanations

    phrases related to the launch of campaigns or attacks

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of initiating or starting campaigns or projects

    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
     Marketable
    -0.75
    Son
    -0.71
    iane
    -0.66
    avering
    -0.64
    GO
    -0.63
    cious
    -0.62
    uth
    -0.61
    etry
    -0.61
    how
    -0.58
    Jose
    -0.58
    POSITIVE LOGITS
    launch
    0.91
    laun
    0.89
    eers
    0.86
    pad
    0.85
     Seym
    0.83
    lishing
    0.81
    wcs
    0.80
     launching
    0.79
    eer
    0.76
    EStream
    0.75
    Activations Density 0.034%

    No Known Activations