INDEX

Explanations

adjectives that convey importance or significant qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

\{\\

-0.51

:+:

-0.47

テンツ

-0.46

༘

-0.42

 tanggung

-0.42

Activités

-0.42

 poveznice

-0.41

adaptiveStyles

-0.40

सन्दर्भ

-0.40

 OMITBAD

-0.40

POSITIVE LOGITS

 Very

1.02

 very

0.98

Very

0.96

very

0.87

 VERY

0.83

 Bardzo

0.83

 Très

0.81

非常好

0.81

VERY

0.79

 Очень

0.77

Activations Density 0.379%

adjectives that convey importance or significant qualities

No Comments

No Known Activations