INDEX

Explanations

phrases that discuss partial involvement or contributions in various contexts

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

 Roskov

-0.97

AndEndTag

-0.80

 fallu

-0.71

MigrationBuilder

-0.70

المناصب

-0.69

 SwitchCompat

-0.65

Przypisy

-0.64

nesty

-0.64

GEBURTSDATUM

-0.62

estacks

-0.61

POSITIVE LOGITS

部分

1.03

 portion

1.01

 部分

0.96

 parte

0.95

 part

0.92

 portions

0.91

一部分

0.89

 partially

0.89

part

0.89

Часть

0.86

Activations Density 0.330%

phrases that discuss partial involvement or contributions in various contexts

No Comments

No Known Activations