INDEX

Explanations

phrases related to conditions or constraints

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

"in mind" phrase

np_acts-logits-general · gemini-2.0-flash

in mind

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

bootstrapcdn

-0.54

хьтан

-0.52

λιά

-0.48

oches

-0.47

ArgsConstructor

-0.47

aragus

-0.45

%")

-0.44

gridx

-0.44

')")

-0.43

Dx

-0.43

POSITIVE LOGITS

 mind

3.27

mind

2.50

 Mind

2.27

Mind

2.21

 MIND

2.16

 minds

2.01

 mente

1.75

MIND

1.74

minds

1.45

 minde

1.42

Activations Density 0.151%

phrases related to conditions or constraints

"in mind" phrase

in mind

No Comments

No Known Activations