INDEX

Explanations

references to quantities or frequency, particularly involving the word "many."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 assic

-0.65

Aws

-0.65

 thingy

-0.59

 valami

-0.58

MigrationBuilder

-0.58

cault

-0.56

 noget

-0.55

 qualcosa

-0.55

something

-0.55

 rimb

-0.53

POSITIVE LOGITS

 many

1.11

 Many

1.03

Many

1.02

MANY

1.01

many

1.00

 MANY

0.92

 vieler

0.90

 muchos

0.88

 Многие

0.87

Muchos

0.87

Activations Density 0.191%

references to quantities or frequency, particularly involving the word "many."

No Comments

No Known Activations