INDEX

Explanations

terms related to medical treatments or therapies

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

Parcelize

-0.61

Rhestr

-0.58

makeText

-0.57

DriverManager

-0.57

 AssemblyTitle

-0.57

nean

-0.56

 NSCoder

-0.55

WebElementEntity

-0.54

 uovo

-0.53

MethodManager

-0.52

POSITIVE LOGITS

 насељу

0.55

ti

0.52

্ত

0.52

didSet

0.51

 strtok

0.50

EMPO

0.50

 spiro

0.49

 atoi

0.49

son

0.49

 piti

0.48

Activations Density 0.137%

terms related to medical treatments or therapies

No Comments

No Known Activations