INDEX

Explanations

references to consistency and quality 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 @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

TargetException

-0.86

Personendaten

-0.68

ètement

-0.67

 للمعارف

-0.65

posedge

-0.64

țion

-0.62

requireNonNull

-0.62

adget

-0.59

 apellidos

-0.59

ADVERTISEMENT

-0.59

POSITIVE LOGITS

consistent

1.03

 consistency

0.99

 consistent

0.98

consistency

0.95

Consistency

0.93

 inconsistent

0.83

Consistent

0.83

 Consistency

0.81

 Consistent

0.78

 pinulongan

0.76

Activations Density 0.099%

references to consistency and quality in various contexts

No Comments

No Known Activations