INDEX

Explanations

important notes or annotations in the text

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

addPreferredGap

-0.67

athread

-0.63

WaitGroup

-0.61

Enllaces

-0.60

inerja

-0.60

complexType

-0.60

Хьажоргаш

-0.59

buttonShape

-0.59

subfigure

-0.57

POSITIVE LOGITS

Note

0.82

 NOTE

0.82

 note

0.81

NOTE

0.81

 Note

0.79

note

0.67

ちなみに

0.63

if

0.61

Disclaimer

0.56

 caveat

0.56

Activations Density 0.276%

important notes or annotations in the text

No Comments

No Known Activations