INDEX

Explanations

phrases that involve spoken dialogue or reported speech

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 EconPapers

-0.84

 Majefty

-0.82

 CreateTagHelper

-0.79

SharedDtor

-0.79

 purpoſe

-0.75

 houſe

-0.74

 autorytatywna

-0.74

 ſtate

-0.73

utilisons

-0.73

 Pingback

-0.71

POSITIVE LOGITS

 laugh

0.64

 laughed

0.61

 laughing

0.55

 laughs

0.54

 chuckled

0.52

Laughing

0.51

laughs

0.51

 RequestMethod

0.50

laugh

0.50

ArgsConstructor

0.50

Activations Density 0.062%

phrases that involve spoken dialogue or reported speech

No Comments

No Known Activations