INDEX

Explanations

statements made by individuals or representatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

databind

-0.79

LookAnd

-0.66

 play

-0.62

 themselves

-0.59

CRY

-0.59

themselves

-0.59

 Play

-0.58

 Morty

-0.58

 yourselves

-0.58

лосо

-0.58

POSITIVE LOGITS

 said

0.90

said

0.79

<bos>

0.71

HasAnnotation

0.69

 SAID

0.67

Бахар

0.64

 trebui

0.64

الحياه

0.62

>{@

0.62

agaimana

0.61

Activations Density 0.112%

statements made by individuals or representatives

No Comments

No Known Activations