INDEX

Explanations

references to entities involved in publishing or leadership roles

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

ending in "er" or "ers"

np_acts-logits-general · gemini-2.0-flash

roles ending in er or or

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

-0.61

-0.59

-0.55

tazione

-0.53

-0.52

und

-0.50

addContainerGap

-0.50

it

-0.50

“

-0.49

POSITIVE LOGITS

 Monfieur

1.13

Efq

1.12

 whoſe

1.11

 Theſe

1.02

 myſelf

1.01

 pleaſure

0.99

 Perſ

0.99

 perſon

0.97

Eſ

0.97

 houſe

0.96

Activations Density 0.410%

references to entities involved in publishing or leadership roles

ending in "er" or "ers"

roles ending in er or or

No Comments

No Known Activations