INDEX

Explanations

expressions of admiration or being impressed by something or someone

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

 Holman

-0.70

 contrario

-0.65

 Fielding

-0.62

 akar

-0.58

InjectMocks

-0.57

zeman

-0.57

Dal

-0.57

 civile

-0.56

nO

-0.55

 Whyte

-0.55

POSITIVE LOGITS

 impress

2.15

 impressed

2.02

 impressions

1.86

 impression

1.85

 Impression

1.81

Impressive

1.80

impres

1.80

 impres

1.69

Imp

1.63

impression

1.63

Activations Density 0.062%

expressions of admiration or being impressed by something or someone

No Comments

No Known Activations