INDEX

Explanations

references to "real" or "actual" situations and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

numerusform

-0.89

 alphabetically

-0.85

StoryboardSegue

-0.81

 ardından

-0.80

 Montrose

-0.79

 pinulongan

-0.79

 emprender

-0.78

 brevemente

-0.77

hoodie

-0.76

yntaxException

-0.75

POSITIVE LOGITS

 real

3.49

 Real

3.04

real

3.03

Real

3.03

 REAL

2.91

REAL

2.83

getReal

1.97

 реаль

1.91

 reales

1.91

 reale

1.87

Activations Density 0.051%

references to "real" or "actual" situations and concepts

No Comments

No Known Activations