INDEX

Explanations

references to specific geographical locations and their contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

ิ้ง

-0.66

InvalidProtocol

-0.58

 houſe

-0.53

 fevere

-0.53

 Theſe

-0.52

InjectAttribute

-0.51

 variation

-0.51

 ſtate

-0.50

 fufficient

-0.49

 Erişim

-0.49

POSITIVE LOGITS

 مشين

0.72

 يتيمه

0.71

 تانيه

0.68

balleur

0.68

 "..\..\

0.64

 <=",

0.62

aarrggbb

0.62

 חיצוניים

0.59

 "..\..\..\

0.56

באנגלית

0.55

Activations Density 0.885%

references to specific geographical locations and their contexts

No Comments

No Known Activations