INDEX

Explanations

references to alcohol and substance use

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

RegressionTest

-0.73

zag

-0.66

 AttributeSet

-0.65

appartamento

-0.63

Swar

-0.63

 Envelope

-0.61

𝟹

-0.60

fromCharCode

-0.60

 Schulte

-0.60

Zag

-0.59

POSITIVE LOGITS

 beer

1.72

Beer

1.53

 BEER

1.52

 Beer

1.51

 alcohol

1.47

 beers

1.40

beer

1.39

Alcohol

1.38

 Alcohol

1.37

 alcohols

1.33

Activations Density 0.144%

references to alcohol and substance use

No Comments

No Known Activations