INDEX

Explanations

mathematical references and formal assertions within the text

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

ValueStyle

-0.62

ąd

-0.55

ModelAdmin

-0.54

endance

-0.53

Tikang

-0.52

 onAnimation

-0.51

PagerAdapter

-0.49

 Pró

-0.47

שע

-0.47

 spieg

-0.47

POSITIVE LOGITS

let

1.32

Let

1.22

Let

1.14

 Suppose

1.03

 suppose

1.01

 consider

1.01

Suppose

0.97

 Consider

0.96

let

0.95

Пусть

0.94

Activations Density 1.213%

mathematical references and formal assertions within the text

No Comments

No Known Activations