INDEX

Explanations

phrases indicating uncertainty or negative sentiments

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

 betweenstory

-1.17

Efq

-1.02

 houſe

-1.01

 Houſe

-1.01

 itſelf

-1.00



-0.99

 raiſ

-0.98

 myſelf

-0.96

 Majefty

-0.94

出版年

-0.91

POSITIVE LOGITS

Theres

0.58

The

0.56

The

0.52

 Theres

0.52

not

0.51

hå

0.51

isa

0.51

 theres

0.50

oplus

0.50

is

0.50

Activations Density 0.110%

phrases indicating uncertainty or negative sentiments

No Comments

No Known Activations