© 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. 1-RES-JB
    11. 14598
    Prev
    Next
    INDEX
    Explanations

    domain names or references to domains

    oai_token-act-pair · gpt-3.5-turbo

    references to domain names and their various aspects or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clement
    -0.79
     Irving
    -0.79
     Fulton
    -0.71
     Hayward
    -0.69
    tics
    -0.69
     Dek
    -0.66
     Wheat
    -0.65
    burgh
    -0.64
     Ol
    -0.63
     Miche
    -0.63
    POSITIVE LOGITS
     domain
    1.17
     domains
    1.11
     Domain
    1.02
    Domain
    1.01
    domain
    0.98
    iless
    0.88
    wcsstore
    0.77
    masters
    0.76
    ulence
    0.76
    llular
    0.76
    Activations Density 0.008%

    No Known Activations