INDEX

Explanations

punctuation marks, specifically periods

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

HTML paragraph tags

np_acts-logits-general · gemini-2.0-flash

list formatting

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personendaten

-1.23

imageshack

-1.04

MigrationBuilder

-1.02

IntoConstraints

-0.97

 NSCoder

-0.96

parsedMessage

-0.93

出版年

-0.90

ReusableCell

-0.90

mybatisplus

-0.89

AccessorTable

-0.88

POSITIVE LOGITS

The

0.67

It

0.67

 Note

0.61

For

0.59

 However

0.59

 Also

0.58

↵↵

0.57

↵

0.56

If

0.55

 Hence

0.54

Activations Density 0.181%

punctuation marks, specifically periods

HTML paragraph tags

list formatting

No Comments

No Known Activations