INDEX

Explanations

references to user interface elements and notifications in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

pal

-0.54

it

-0.51

<bos>

-0.50

-0.48

__(/*!

-0.47

+/*

-0.47

 text

-0.46

')}}"

-0.46

dite

-0.45

 result

-0.45

POSITIVE LOGITS

脚注の使い方

0.93

makeText

0.93

LENGTH

0.90

SHORT

0.88

 Cæsar

0.84

VersionUID

0.84

Hozzáférés

0.81

BufferException

0.79

 Shakspeare

0.79

 AssemblyCompany

0.77

Activations Density 0.013%

references to user interface elements and notifications in code

No Comments

No Known Activations