INDEX

Explanations

expressions related to evaluation and enjoyment criteria

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

a minimum value ("at least")

np_acts-logits-general · gemini-2.0-flash

at least

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

 كومونز

-0.80

enumii

-0.64

 فريبيس

-0.62

iNdEx

-0.61

AxisAlignment

-0.60

ագրություններ

-0.57

 contd

-0.56

참고

-0.56

 GenerationType

-0.56

 transfieras

-0.56

POSITIVE LOGITS

 atleast

2.54

at

2.40

 almeno

2.35

至少

2.08

 setidaknya

1.87

少なくとも

1.85

 wenigstens

1.84

 zumindest

1.84

 mindestens

1.82

 حداقل

1.60

Activations Density 1.108%

expressions related to evaluation and enjoyment criteria

a minimum value ("at least")

at least

No Comments

No Known Activations