INDEX

Explanations

negation expressions and negative conditions

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

pmatrix

-0.60

Guaranteed

-0.53

ingar

-0.52

 MongoClient

-0.52

 potentialities

-0.52

PYX

-0.51

 unica

-0.50

SIN

-0.50

SqlClient

-0.50

homonymie

-0.50

POSITIVE LOGITS

(!__

0.98

enumi

0.83

 epä

0.77

 الدولى

0.77

AutoresizingMask

0.75

 Chwiliwch

0.73

(!$

0.72

 المعيارى

0.71

enumii

0.70

 isinstance

0.70

Activations Density 0.075%

negation expressions and negative conditions

No Comments

No Known Activations