INDEX

Explanations

references to clinical studies and case reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 allemaal

-0.84

ſelf

-0.84

 itſelf

-0.79

Efq

-0.79

脚注の使い方

-0.78

 wireType

-0.78

 purpoſe

-0.77

 Theſe

-0.76

 whoſe

-0.76

ſy

-0.75

POSITIVE LOGITS

two

0.98

 Both

0.92

 beiden

0.90

 both

0.90

Two

0.89

Both

0.87

 ambos

0.87

two

0.82

both

0.81

 beide

0.80

Activations Density 1.577%

references to clinical studies and case reports

No Comments

No Known Activations