INDEX

Explanations

terms related to direct evidence 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 @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

WireFormatLite

-0.65

 يتيمه

-0.64

Obrázky

-0.62

viewDidLoad

-0.61

 JpaRepository

-0.61

vician

-0.60

heartedly

-0.60

BeginContext

-0.58

ագրություններ

-0.58

MigrationBuilder

-0.56

POSITIVE LOGITS

 trực

0.58

Assista

0.57

 artistique

0.55

ėd

0.54

неопр

0.52

 مستقیم

0.51

—

0.51

 diretta

0.51

sigmoid

0.50

codiles

0.49

Activations Density 0.284%

terms related to direct evidence in various contexts

No Comments

No Known Activations