INDEX

Explanations

occurrences of the term "text" and its variations within the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

coroutines

-0.90

Epidemiology

-0.70

DebuggerNonUser

-0.68

دانشنامهٔ

-0.66

Jereo

-0.64

Отзывы

-0.63

IBarButtonItem

-0.62

WriteBarrier

-0.60

 combineReducers

-0.59

RepeatedField

-0.59

POSITIVE LOGITS

 text

4.17

 Text

4.10

Text

3.78

 TEXT

3.73

TEXT

3.71

text

3.65

 texts

3.25

 texte

2.78

 texto

2.76

 Texts

2.76

Activations Density 0.062%

occurrences of the term "text" and its variations within the document

No Comments

No Known Activations