INDEX

Explanations

instances of words or phrases related to addition or inclusion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

تقاوى

-0.65

maketitle

-0.63

tymologie

-0.61

Bibliografia

-0.61

########.

-0.60

DOCTYPE

-0.60

::::::::

-0.60

achie

-0.60

nestjs

-0.58

Bism

-0.57

POSITIVE LOGITS

 added

1.34

add

1.24

 adds

1.23

 Adds

1.22

Added

1.19

Adding

1.17

 Adding

1.17

 adding

1.15

 aggiunge

1.15

Add

1.13

Activations Density 0.165%

instances of words or phrases related to addition or inclusion

No Comments

No Known Activations