INDEX

Explanations

terms related to cooling processes or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 CURIAM

-0.72

 الحره

-0.68

DJANGO

-0.68

 high

-0.66

IANT

-0.62

low

-0.62

romptu

-0.60

 short

-0.59

########.

-0.59

 clean

-0.57

POSITIVE LOGITS

 softening

1.73

 soften

1.61

 tightening

1.57

 deepening

1.53

 softens

1.51

 softened

1.51

 strengthening

1.50

 shortening

1.44

 weakening

1.43

strengthen

1.42

Activations Density 0.154%

terms related to cooling processes or systems

No Comments

No Known Activations