INDEX

Explanations

instances of the word "read" and its variations, often in context related to reading data or instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

帖最后由

-0.94

 MonoBehaviour

-0.89

ConstraintMaker

-0.84

makeConstraints

-0.73

Jegyzetek

-0.70

ьаж

-0.70

 Lightboxes

-0.69

ButterKnife

-0.69

 createSprite

-0.68

 AppCompatTheme

-0.66

POSITIVE LOGITS

 aloud

1.06

justed

0.87

 atenta

0.77

 comprehension

0.75

ying

0.68

ahead

0.65

mitted

0.65

 books

0.63

iness

0.61

apt

0.61

Activations Density 0.122%

instances of the word "read" and its variations, often in context related to reading data or instructions

No Comments

No Known Activations