INDEX

Explanations

references to legal agreements and negotiations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ſelves

-1.07

Efq

-1.04

 myſelf

-1.04

 purpoſe

-0.99

 Monfieur

-0.99

ſelf

-0.97

 Majefty

-0.91

 Jefus

-0.91

 Conſ

-0.90

 itſelf

-0.88

POSITIVE LOGITS

 still

0.66

 nevertheless

0.61

still

0.56

Still

0.56

 nonetheless

0.53

 Nevertheless

0.52

 Still

0.50

 trotzdem

0.50

Nevertheless

0.49

 STILL

0.49

Activations Density 0.249%

references to legal agreements and negotiations

No Comments

No Known Activations