© 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. 2-RES-JB
    11. 24112
    Prev
    Next
    INDEX
    Explanations

    words related to law enforcement or security

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and labels of people and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStream
    -0.82
    ĵĺ
    -0.67
     fame
    -0.64
    EStreamFrame
    -0.64
     bottleneck
    -0.63
     guarding
    -0.63
     compromising
    -0.62
    doors
    -0.61
    ãĤ¼ãĤ¦ãĤ¹
    -0.60
     laying
    -0.60
    POSITIVE LOGITS
    ogether
    0.78
    oby
    0.78
    romeda
    0.77
    olly
    0.77
    arry
    0.75
    agascar
    0.75
    notations
    0.74
    arl
    0.72
    arks
    0.71
    rea
    0.70
    Activations Density 0.303%

    No Known Activations