INDEX

Explanations

the word "to"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

baix

-0.71

 daudz

-0.68

vats

-0.61

้าน

-0.60

绝

-0.59

ots

-0.58

peč

-0.58

FOR

-0.58

For

-0.57

FORMAN

-0.57

POSITIVE LOGITS

0.79

 estimés

0.78

 gustaría

0.78

 Gonna

0.77

 shawl

0.77

 Nicho

0.76

PerformLayout

0.75

be

0.75

 Wanna

0.72

WIC

0.72

Activations Density 0.116%

the word "to"

No Comments

No Known Activations