© 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. 17854
    Prev
    Next
    INDEX
    Explanations

    references to various agencies and organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various agencies

    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
    aunder
    -0.75
    sbm
    -0.74
    cial
    -0.73
    cific
    -0.67
    itious
    -0.67
    ching
    -0.67
    neapolis
    -0.67
    isers
    -0.65
    construct
    -0.65
    bring
    -0.64
    POSITIVE LOGITS
     Agency
    1.07
    encies
    0.82
     Administrator
    0.82
     Authority
    0.80
    ENCY
    0.78
     agencies
    0.76
     agency
    0.73
     Employees
    0.71
     Headquarters
    0.70
     Directorate
    0.68
    Activations Density 0.015%

    No Known Activations