INDEX

Explanations

repeated patterns or sequences in data

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

archaic or non-English words

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

er

-1.15

ers

-0.96

ER

-0.74

“

-0.74

erne

-0.70

Bo

-0.66

ه

-0.66

 Finney

-0.66

CAL

-0.65

VER

-0.65

POSITIVE LOGITS

1.38

 nakalista

1.15

 Majefty

1.04

 referenties

0.99

 itſelf

0.98

 myſelf

0.96

 дописавши

0.95

tadora

0.89

 schia

0.89

 وتسجيلات

0.87

Activations Density 0.044%

repeated patterns or sequences in data

archaic or non-English words

No Comments

No Known Activations