INDEX

Explanations

direct quotations or speech in the text

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

ENEFITS

-0.74

ANCIAL

-0.71

bufio

-0.69

िखित

-0.69

 IBRARY

-0.68

ffions

-0.67

Confira

-0.65

ICAGO

-0.64

SpringBootTest

-0.63

duled

-0.63

POSITIVE LOGITS

“

0.92

0.69

“

0.67

：“

0.67

0.66

 <<<<<<<<<<<<<<

0.64

”

0.62

 frankly

0.58

Jeografia

0.56

all

0.56

Activations Density 0.054%

direct quotations or speech in the text

No Comments

No Known Activations