INDEX

Explanations

terms related to medical conditions and syndromes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PerformLayout

-0.84

aarrggbb

-0.77

AntiForgeryToken

-0.76

 متعلقه

-0.74

 EconPapers

-0.73

IntoConstraints

-0.72

 defaultstate

-0.67

IVEREF

-0.65

 Pristupljeno

-0.64

OwnProperty

-0.62

POSITIVE LOGITS

 derived

0.88

 root

0.87

derived

0.84

root

0.78

 derives

0.77

 derive

0.77

 Derived

0.75

 deriva

0.74

 ROOT

0.72

Derived

0.70

Activations Density 0.240%

terms related to medical conditions and syndromes

No Comments

No Known Activations