INDEX

Explanations

references to seriousness or gravity in the context discussed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 ویکی‌پدی

-0.72

ReusableCell

-0.64

 snippetHide

-0.62

ClientRect

-0.60

 Paglinawan

-0.56

httphttps

-0.56

曖昧さ回避

-0.51

 كومونز

-0.51

 AssemblyCulture

-0.51

balleur

-0.50

POSITIVE LOGITS

 serious

1.06

 seriousness

1.05

serious

1.05

Serious

1.03

 Serious

1.00

 serio

0.83

 sérieux

0.83

 sério

0.77

 serius

0.74

 серьез

0.73

Activations Density 0.017%

references to seriousness or gravity in the context discussed

No Comments

No Known Activations