© 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. 23925
    Prev
    Next
    INDEX
    Explanations

    phrases related to quoting someone

    oai_token-act-pair · gpt-3.5-turbo

    instances of dialogue or quotations

    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
    spir
    -0.86
    mol
    -0.85
    thur
    -0.80
    etheless
    -0.80
    enfranch
    -0.74
     collided
    -0.72
     neighb
    -0.70
    eneg
    -0.70
     interfered
    -0.70
    erity
    -0.69
    POSITIVE LOGITS
     Sgt
    0.91
     Diane
    0.88
     Geoff
    0.86
     Donna
    0.86
     Mike
    0.83
     analyst
    0.82
     Nina
    0.82
     Angela
    0.82
     Kathleen
    0.81
     Dana
    0.81
    Activations Density 0.053%

    No Known Activations