INDEX

Explanations

clothing items or fashion-related descriptors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 June

-0.56

June

-0.53

 July

-0.52

 cref

-0.51

 Juin

-0.50

 watermelon

-0.49

 lysis

-0.48

July

-0.48

 Watermelon

-0.47

JULY

-0.47

POSITIVE LOGITS

 warm

1.59

 warmth

1.59

 Warm

1.48

 warming

1.43

Warm

1.42

warm

1.40

 warmest

1.39

 warmer

1.38

 warms

1.37

 WARM

1.34

Activations Density 0.172%

clothing items or fashion-related descriptors

No Comments

No Known Activations