© 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. 18835
    Prev
    Next
    INDEX
    Explanations

    phrases related to family relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to familial relationships and connections

    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
    IUM
    -0.76
    omsky
    -0.64
     Tycoon
    -0.63
     Sounds
    -0.59
     Transcript
    -0.57
     Guys
    -0.56
     Areas
    -0.56
     Atmosp
    -0.55
     RELEASE
    -0.55
     Hacker
    -0.55
    POSITIVE LOGITS
    law
    1.26
    laws
    1.05
     law
    1.02
     arms
    0.93
    Law
    0.90
    brother
    0.76
    arms
    0.74
     crime
    0.74
     counsel
    0.74
    nesota
    0.72
    Activations Density 0.068%

    No Known Activations