© 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. 2-RES-JB
    11. 3076
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific company or product names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Nexen" and references to "iPods" and the name "Erin."

    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
    sea
    -0.78
     Bapt
    -0.76
     bapt
    -0.73
     squid
    -0.68
    ©¶æ
    -0.67
     parchment
    -0.65
     unst
    -0.65
     carrot
    -0.64
    =-=-=-=-=-=-=-=-
    -0.64
    imental
    -0.64
    POSITIVE LOGITS
    ptives
    1.00
    adr
    0.95
     Nex
    0.90
    arios
    0.85
    kson
    0.84
    naires
    0.82
     Finder
    0.81
     Occupations
    0.79
    enhagen
    0.72
    nil
    0.71
    Activations Density 0.032%

    No Known Activations