© 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. 11-RES-JB
    11. 9860
    Prev
    Next
    INDEX
    Explanations

    references to specific chemicals, organizations, and technical entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific chemicals or substances and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.64
    Topics
    -0.59
    emetery
    -0.57
    CVE
    -0.56
    cture
    -0.54
    SHIP
    -0.54
    natureconservancy
    -0.52
    nces
    -0.52
    EH
    -0.52
    zai
    -0.50
    POSITIVE LOGITS
     infamous
    0.81
     famed
    0.75
     likes
    0.74
     notorious
    0.67
     defunct
    0.66
     immensely
    0.66
     disgr
    0.64
     Kardash
    0.64
     Dalai
    0.64
     hugely
    0.64
    Activations Density 0.270%

    No Known Activations