INDEX

Explanations

references to locations or geographic entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ViewImports

-0.69

 CreateTagHelper

-0.66

HomeAsUpEnabled

-0.66

 IBOutlet

-0.65

 AssemblyTitle

-0.61

ViewFeatures

-0.61

榄

-0.60

 Raton

-0.58

enderror

-0.56

UnusedPrivate

-0.56

POSITIVE LOGITS

 York

0.95

 Yorkshire

0.89

York

0.88

 YORK

0.86

YORK

0.81

 york

0.81

Yorkshire

0.73

york

0.73

 Yorkers

0.71

 Leeds

0.68

Activations Density 0.140%

references to locations or geographic entities

No Comments

No Known Activations