INDEX

Explanations

specific patterns or identifiers related to system processes or logs

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

+#+#

-0.89

########.

-0.79

Hauptartikel

-0.74

WriteLiteral

-0.73

InSection

-0.72

AnchorStyles

-0.71

PhysRevD

-0.71

 oprot

-0.71

 ویکی‌پدیای

-0.70

sizeCache

-0.69

POSITIVE LOGITS

 Majefty

0.57

 متعلقه

0.54

enumi

0.50

0.46

 exercise

0.44

 کردیم

0.43

 exerc

0.43

 substitutes

0.43

 twist

0.43

ennes

0.42

Activations Density 0.065%

specific patterns or identifiers related to system processes or logs

No Comments

No Known Activations