© 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. 17763
    Prev
    Next
    INDEX
    Explanations

    textual symbols commonly used to convey emotion or tone

    oai_token-act-pair · gpt-3.5-turbo

    references to self and personal responsibility

    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
     adolesc
    -0.70
     Broadcasting
    -0.70
     Rosenthal
    -0.70
    ickets
    -0.67
     Trinidad
    -0.66
     CLR
    -0.65
     Avalon
    -0.64
     friction
    -0.64
     guiActiveUnfocused
    -0.64
     paperback
    -0.64
    POSITIVE LOGITS
    own
    1.08
    should
    1.00
    must
    0.98
    agree
    0.97
    swer
    0.96
    ï¸ı
    0.96
     deserve
    0.92
    ve
    0.91
    tal
    0.90
    audi
    0.89
    Activations Density 0.159%

    No Known Activations