INDEX

Explanations

statements of blame or self-recrimination

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

 oprot

-0.88

Iné

-0.68

 ―――――

-0.66

NUMX

-0.66

 незавершена

-0.65

 Houſe

-0.65

cknow

-0.65

 Monfieur

-0.65

 NDEBUG

-0.65

 itſelf

-0.64

POSITIVE LOGITS

0.57

!!!

0.55

!!

0.53

!!!!

0.52

!”

0.50

!"

0.48

0.47

ufen

0.44

 inspiração

0.44

Activations Density 0.193%

statements of blame or self-recrimination

No Comments

No Known Activations