INDEX

Explanations

references to medical treatments and their effects

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

Ohm

-0.75

GraphicsUnit

-0.75

Efq

-0.71

ohm

-0.68

ngdoc

-0.67

endphp

-0.67

 drau

-0.67

abestanden

-0.67

WebpackPlugin

-0.66

StandardCharsets

-0.65

POSITIVE LOGITS

TREAT

0.89

 TREAT

0.88

 treat

0.87

treat

0.86

 Treat

0.84

 treats

0.83

 treating

0.81

 Treating

0.81

Treat

0.80

Treating

0.78

Activations Density 0.160%

references to medical treatments and their effects

No Comments

No Known Activations