INDEX

Explanations

references to reading or reviewing something in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

contentLoaded

-0.69

WindowConstants

-0.65

)"),

-0.64

onViewCreated

-0.63

)');

-0.62

theless

-0.60

uality

-0.59

 Unito

-0.59

}{*}{

-0.58

zeiti

-0.57

POSITIVE LOGITS

netbeans

0.61

ValueStyle

0.57

 beginnetje

0.53

anskje

0.51

جموع

0.49

 Patil

0.48

indakan

0.47

yethylene

0.47

مصادر

0.45

 utafitiHapana

0.45

Activations Density 0.261%

references to reading or reviewing something in the text

No Comments

No Known Activations