INDEX

Explanations

programming constructs related to conditional logic and boolean values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 mistaken

-0.67

 inaccurate

-0.66

 erroneous

-0.63

 deceive

-0.63

 falsely

-0.59

 lied

-0.59

 errone

-0.58

 erroneously

-0.58

 misplaced

-0.58

 misguided

-0.57

POSITIVE LOGITS

 true

1.01

true

0.99

 True

0.81

 TRUE

0.79

 verdaderas

0.78

True

0.77

TRUE

0.77

 verdade

0.74

 verdadeiro

0.74

 verdadero

0.72

Activations Density 0.102%

programming constructs related to conditional logic and boolean values

No Comments

No Known Activations