INDEX

Explanations

references to specific people or characters in conjunction with their titles or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 GlobalKey

-0.69

MemoryWarning

-0.68

 Theſe

-0.67

 للمعارف

-0.66

 AppColors

-0.62

Efq

-0.61

 Chriſt

-0.60

 itſelf

-0.56

 dispositif

-0.56

ſelf

-0.56

POSITIVE LOGITS

 OFDb

0.53

 jadx

0.51

SerializedName

0.50

 <=",

0.49

artan

0.49

Jegyzetek

0.49

bootstrapcdn

0.48

GenerationType

0.48

edb

0.47

ذن

0.47

Activations Density 0.296%

references to specific people or characters in conjunction with their titles or roles

No Comments

No Known Activations