INDEX

Explanations

expressions related to perception and recognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

<bos>

-0.73

Tikang

-0.56

ритори

-0.51

IVersion

-0.50

 pavillon

-0.48

yordu

-0.47

 ErrInvalid

-0.47

 satisfaire

-0.47

IEnumerator

-0.47

 wiedzy

-0.46

POSITIVE LOGITS

 AssemblyCulture

0.84

ьаж

0.62

HtmlAttribute

0.61

 Picchu

0.59

 realize

0.58

AddTagHelper

0.58

InjectAttribute

0.56

 ویکی‌پدی

0.56

 propOrder

0.55

Zeneca

0.55

Activations Density 0.277%

expressions related to perception and recognition

No Comments

No Known Activations