INDEX

Explanations

negative assessments of performance or quality

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

 Reverso

-0.63

 iprot

-0.52

SOUNDBITE

-0.51

!”

-0.49

mulos

-0.49

!’

-0.49

!!!”

-0.48

 angeb

-0.48

!”.

-0.48

 Talley

-0.47

POSITIVE LOGITS

Somewhat

0.78

有点

0.72

有些不

0.72

 sometimes

0.71

 agak

0.69

 Somewhat

0.69

 somewhat

0.68

やや

0.68

有點

0.68

somewhat

0.67

Activations Density 0.432%

negative assessments of performance or quality

No Comments

No Known Activations