INDEX

Explanations

phrases and words related to evaluation and judgment

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

obviousness or common knowledge

np_acts-logits-general · gemini-2.0-flash

of course

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

zzleHttp

-0.56

 PeEnEo

-0.56

windowFixed

-0.55

 utafitiHapana

-0.53

AppCompat

-0.53

InitStruct

-0.50

namentales

-0.50

ſelves

-0.49

uttosto

-0.49

ositol

-0.48

POSITIVE LOGITS

 obviously

2.13

 ovviamente

2.12

obviously

2.06

ofc

2.02

 évidemment

1.99

 obviamente

1.93

 natürlich

1.92

 Obviously

1.85

 natuurlijk

1.84

 oczywiście

1.80

Activations Density 0.563%

phrases and words related to evaluation and judgment

obviousness or common knowledge

of course

No Comments

No Known Activations