INDEX

Explanations

occurrences of the word "new"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 GetComponent

-0.66

 ItemStack

-0.62

 Pilate

-0.61

 butterknife

-0.60

usercontent

-0.60

 RIAA

-0.59

 AssertionError

-0.59

 uParam

-0.59

 onPause

-0.58

 BufferedImage

-0.57

POSITIVE LOGITS

new

4.32

new

3.71

 nueva

3.16

 nuevo

3.06

 nuevos

3.05

新

3.05

NEW

3.03

 nieuwe

2.98

 nuevas

2.98

New

2.90

Activations Density 0.114%

occurrences of the word "new"

No Comments

No Known Activations