© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23423
    Prev
    Next
    INDEX
    Explanations

    names of specific locations or entities, especially related to technology or organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names, particularly those of locations and entities

    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
    udeb
    -0.84
     actionGroup
    -0.66
     antidepress
    -0.64
    natureconservancy
    -0.63
    dyl
    -0.62
    soDeliveryDate
    -0.62
    chard
    -0.62
    rael
    -0.62
     Nicarag
    -0.62
    older
    -0.61
    POSITIVE LOGITS
     County
    0.81
     Valley
    0.81
    Gate
    0.81
     Heights
    0.77
     Hath
    0.73
     Airways
    0.73
     Grove
    0.71
     Island
    0.69
     Disk
    0.69
     Prize
    0.69
    Activations Density 0.359%

    No Known Activations