INDEX

Explanations

the beginning of a text document or section, particularly signals indicating the start of a new paragraph or topic

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

HTML italic tag `<em>`

np_acts-logits-general · gemini-2.0-flash

question words and specific nouns

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

 EClass

-0.82

 AttributeSet

-0.79

AllAfrica

-0.77

InjectAttribute

-0.74

MockBean

-0.74

extAlignment

-0.73

NUMX

-0.71

 pers

-0.71

otheby

-0.70

 vPvB

-0.69

POSITIVE LOGITS

<em>

1.09

<strong>

0.98

 termica

0.91

 quæ

0.89

The

0.88

 theſe

0.87

What

0.87

Note

0.85

 thoſe

0.84

Also

0.84

Activations Density 0.025%

the beginning of a text document or section, particularly signals indicating the start of a new paragraph or topic

HTML italic tag `<em>`

question words and specific nouns

No Comments

No Known Activations