INDEX

Explanations

occurrences of the word "short" 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ModelExpression

-0.94

 AssemblyVersion

-0.87

 referenties

-0.82

 وتسجيلات

-0.75

ніципалі

-0.73

GEBURTSDATUM

-0.72

odeon

-0.71

%)$

-0.70

eleste

-0.70

panou

-0.70

POSITIVE LOGITS

 short

2.48

 SHORT

2.41

 Short

2.40

Short

2.37

short

2.26

SHORT

2.19

 Shorts

1.81

 shorts

1.76

短

1.71

 shorter

1.61

Activations Density 0.086%

occurrences of the word "short" in various contexts

No Comments

No Known Activations