© 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. 10-RES-JB
    11. 2637
    Prev
    Next
    INDEX
    Explanations

    family relationships, particularly mentioning siblings-in-law

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUM
    -0.68
    omsky
    -0.66
    ecause
    -0.61
     Wow
    -0.60
     Cruiser
    -0.60
     RELEASE
    -0.60
    theless
    -0.59
    Newsletter
    -0.59
     Whitman
    -0.58
    llan
    -0.55
    POSITIVE LOGITS
    iti
    0.88
    law
    0.83
     law
    0.80
    je
    0.80
     exile
    0.78
    jury
    0.76
     arms
    0.74
    animate
    0.71
    command
    0.71
    jured
    0.71
    Activations Density 0.051%

    No Known Activations