© 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. 4-RES-JB
    11. 22174
    Prev
    Next
    INDEX
    Explanations

    words related to nobility, specifically variations of the word "lad"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "lad" and its various contexts, particularly in relation to rankings or categories

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

    No Comments

    Negative Logits
    ãģ®éŃĶ
    -0.71
    OLOG
    -0.70
    porting
    -0.70
    ãĥīãĥ©
    -0.68
    ournal
    -0.68
     Somalia
    -0.67
    oldown
    -0.66
     HRC
    -0.66
     womb
    -0.66
     Somali
    -0.65
    POSITIVE LOGITS
    der
    1.07
    imir
    0.98
    anche
    0.88
    itionally
    0.88
    ys
    0.86
    rian
    0.86
    arov
    0.83
    akh
    0.82
    mir
    0.81
     Lad
    0.78
    Activations Density 0.013%

    No Known Activations