© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 9500
    Prev
    Next
    INDEX
    Explanations

    names of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly Lauren and Arnold

    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
    oleon
    -0.82
    aret
    -0.79
    dev
    -0.70
    olitan
    -0.69
    PER
    -0.69
    enary
    -0.67
    requency
    -0.66
    umbn
    -0.65
    hov
    -0.65
    HAEL
    -0.65
    POSITIVE LOGITS
     Schwarzenegger
    0.90
     Palmer
    0.82
     Akin
    0.75
     Hatch
    0.72
    heit
    0.69
    holm
    0.69
     Luthor
    0.67
    kamp
    0.66
     Fein
    0.64
    ovan
    0.64
    Activations Density 0.108%

    No Known Activations