INDEX

Explanations

references to legal or judicial terms 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 @ 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

mybatisplus

-1.12

 بيها

-0.75

alsh

-0.75

<h5>

-0.73

AsUp

-0.69

 tamu

-0.61

Folks

-0.60

gradle

-0.59

 Brito

-0.59

POSITIVE LOGITS

↵↵↵↵↵↵↵↵

1.62

↵↵↵↵↵↵

1.55

↵↵↵↵↵

1.54

↵↵↵↵↵↵↵↵↵↵↵

1.51

↵↵↵↵↵↵↵↵↵↵

1.47

verwijspagina

1.45

↵↵↵↵↵↵↵

1.44

↵↵↵↵↵↵↵↵↵↵↵↵↵↵

1.38

↵↵↵↵↵↵↵↵↵

1.37

↵↵↵↵↵↵↵↵↵↵↵↵↵

1.37

Activations Density 0.060%

references to legal or judicial terms and concepts

No Comments

No Known Activations