INDEX

Explanations

phrases indicating the first occurrence of an event or action

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 maji

-0.61

multer

-0.61

pygame

-0.59

handelt

-0.57

 Répondre

-0.55

waża

-0.55

Награды

-0.55

 Wiss

-0.54

 hourglass

-0.53

 cabecera

-0.53

POSITIVE LOGITS

 MainAxisSize

0.93

printStackTrace

0.76

 erstmals

0.71

CloseOperation

0.70

ExtendWith

0.70

__(/*!

0.67

首次

0.67

PerformLayout

0.66

 впервые

0.64

第一次

0.64

Activations Density 0.053%

phrases indicating the first occurrence of an event or action

No Comments

No Known Activations