INDEX

Explanations

the term "picture" in various contexts related to visual representation or imagery

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

olesale

-0.94

ConstraintMaker

-0.92

Endnotes

-0.91

horabuena

-0.88

ofollow

-0.87

SBATCH

-0.83

Amicalement

-0.83

juvant

-0.82

Redacción

-0.82

 GenerationType

-0.80

POSITIVE LOGITS

 picture

2.23

 Picture

2.00

picture

1.98

 pictures

1.93

Picture

1.89

 PICTURE

1.85

PICTURE

1.74

 Pictures

1.69

pictures

1.67

Pictures

1.54

Activations Density 0.039%

the term "picture" in various contexts related to visual representation or imagery

No Comments

No Known Activations