INDEX

Explanations

phrases indicating thorough or extensive evaluations and analyses

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

roep

-0.52

 Inversion

-0.50

 okol

-0.49

空き

-0.48

 Feliz

-0.47

tfrac

-0.47

 Trick

-0.46

 למש

-0.46

Predict

-0.46

Noc

-0.46

POSITIVE LOGITS

 comprehensive

2.04

Comprehensive

1.88

comprehensive

1.85

 thorough

1.82

 Comprehensive

1.79

prehensive

1.73

 extensive

1.65

Extensive

1.61

extensive

1.60

 Extensive

1.57

Activations Density 0.199%

phrases indicating thorough or extensive evaluations and analyses

No Comments

No Known Activations