INDEX

Explanations

expressions and phrases related to technical standards and quality management

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

followed by specific suffixes

np_acts-logits-general · gemini-2.0-flash

joining list elements

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

-0.53

-0.52

li

-0.51

os

-0.50

-0.49

pi

-0.49

it

-0.49

POSITIVE LOGITS

 betweenstory

1.05

 GenerationType

0.98

 Мексичка

0.98

StateToProps

0.92

ształ

0.89

 للمعارف

0.88

!("{

0.86

fromCharCode

0.85

"):

0.83

 Majefty

0.81

Activations Density 0.542%

expressions and phrases related to technical standards and quality management

followed by specific suffixes

joining list elements

No Comments

No Known Activations