INDEX

Explanations

references to validation and correctness in context

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

 saites

-0.69

İstinadlar

-0.65

 cref

-0.64

fjspx

-0.58

devamını

-0.57

 الحره

-0.55

 rhestr

-0.55

人之

-0.50

RenderAtEndOf

-0.49

 okuyayım

-0.48

POSITIVE LOGITS

 tslint

0.75

 itſelf

0.75

ſelf

0.71

\<^

0.68

 myſelf

0.66

ſelves

0.66

 purpoſe

0.62

 thoſe

0.62

 ſmall

0.61

 houſe

0.61

Activations Density 0.285%

references to validation and correctness in context

No Comments

No Known Activations