© 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. 17399
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various entities or institutions

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific names or references, particularly the word "Had."

    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
    EStreamFrame
    -0.74
     grace
    -0.69
    SPONSORED
    -0.65
     extraord
    -0.62
     comfort
    -0.59
     Tycoon
    -0.57
     Arpaio
    -0.57
    externalActionCode
    -0.56
     inhabited
    -0.56
     antitrust
    -0.56
    POSITIVE LOGITS
    nesday
    1.26
    ger
    0.98
    amura
    0.94
    rian
    0.93
    iatrics
    0.92
    bach
    0.92
    rien
    0.91
    rig
    0.91
    ria
    0.89
    ril
    0.88
    Activations Density 0.088%

    No Known Activations