© 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. 7082
    Prev
    Next
    INDEX
    Explanations

    references to receiving or not receiving things, such as help, emails, phone calls, explanations, and notices

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of receiving

    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
    occupied
    -0.64
     gaps
    -0.62
    istence
    -0.60
    nown
    -0.60
     Doors
    -0.59
    ween
    -0.58
     loopholes
    -0.58
    Sus
    -0.58
     neighborhoods
    -0.57
     neighbourhoods
    -0.57
    POSITIVE LOGITS
     invitation
    0.93
     accol
    0.91
     permission
    0.90
     blessing
    0.89
     brunt
    0.87
     rebate
    0.85
     notification
    0.85
     congratulations
    0.84
     gift
    0.84
     congrat
    0.83
    Activations Density 0.331%

    No Known Activations