© 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. 7255
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to political figures, particularly the name "Benjamin"

    oai_token-act-pair · gpt-3.5-turbo
    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
    ebook
    -0.86
    uid
    -0.84
    Reviewer
    -0.84
    atics
    -0.81
    TOR
    -0.77
    atically
    -0.77
    ticket
    -0.76
    TPPStreamerBot
    -0.74
    govtrack
    -0.74
    ebin
    -0.73
    POSITIVE LOGITS
    jamin
    1.42
     Franklin
    1.11
     Netanyahu
    1.09
     Witt
    0.85
     Benjamin
    0.84
    itude
    0.78
    heimer
    0.74
     Todd
    0.71
     Harrison
    0.69
     Tucker
    0.69
    Activations Density 0.015%

    No Known Activations