INDEX

Explanations

references to geographical locations and their descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

出版年

-0.81

WriteBarrier

-0.62

CodeAttribute

-0.59

Tikang

-0.59

->$

-0.59

 Italijanski

-0.57

 Paglinawan

-0.56

 CreateTagHelper

-0.55

 دیکھیے

-0.53

зулта

-0.52

POSITIVE LOGITS

Featuring

0.80

 features

0.80

 Featuring

0.76

 feature

0.74

Offering

0.68

 property

0.67

features

0.66

:✨

0.66

 Guests

0.65

 Offering

0.64

Activations Density 0.094%

references to geographical locations and their descriptions

No Comments

No Known Activations