© 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. 7-RES-JB
    11. 23008
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the user to take action

    oai_token-act-pair · gpt-3.5-turbo

    phrases instructing the reader to take action or access information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pard
    -0.67
     defe
    -0.60
     withd
    -0.57
     resc
    -0.55
     taboo
    -0.55
    handedly
    -0.54
     disson
    -0.54
     palate
    -0.54
     experiment
    -0.54
     lik
    -0.53
    POSITIVE LOGITS
     rid
    1.21
    TING
    1.14
    cloneembedreportprint
    0.94
    away
    0.92
    aways
    0.89
     Started
    0.81
     Tickets
    0.79
     Rid
    0.78
     notified
    0.77
     acquainted
    0.76
    Activations Density 0.041%

    No Known Activations