INDEX

Explanations

words related to empirical research and timing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

ValueStyle

-0.81

 мәкал

-0.80

 pleaſure

-0.80

 المعيارى

-0.79

 itſelf

-0.75

 kasarigan

-0.75

 myſelf

-0.72

DoubleQuotes

-0.72

UpInside

-0.71

 artistique

-0.70

POSITIVE LOGITS

<sup>

0.70

<sub>

0.68

Emp

0.62

App

0.61

수

0.58

tay

0.55

Emp

0.54

enken

0.54

docx

0.53

 Membran

0.52

Activations Density 0.108%

words related to empirical research and timing

No Comments

No Known Activations