INDEX

Explanations

instances of the word "normal" and variations of its context

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

 Dreyfus

-0.79

 Riviera

-0.72

💲

-0.72

Dund

-0.71

entyfik

-0.70

 sphinct

-0.67

ktı

-0.66

 Esposito

-0.65

 laissé

-0.65

êmio

-0.64

POSITIVE LOGITS

 normal

2.39

 Normal

2.35

 NORMAL

2.33

normal

2.30

Normal

2.29

NORMAL

2.13

 normals

2.00

 normale

1.93

 normales

1.86

normals

1.71

Activations Density 0.096%

instances of the word "normal" and variations of its context

No Comments

No Known Activations