INDEX

Explanations

formatting markers and structural elements in code or text

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

Code, markdown, or formatting snippets

np_acts-logits-general · gemini-2.0-flash

introduction or conclusion

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

AddTagHelper

-0.73

ChildScrollView

-0.60

 SqlParameter

-0.56

XmlElement

-0.56

 CascadeType

-0.55

UnusedPrivate

-0.54

mybatisplus

-0.54

yntaxException

-0.52

 furthermore

-0.51

AddWithValue

-0.50

POSITIVE LOGITS

 This

0.71

This

0.70

 this

0.66

 Created

0.65

 AssemblyTitle

0.62

Created

0.58

 Class

0.58

 ExecuteAsync

0.57

The

0.57

 Represents

0.57

Activations Density 0.159%

formatting markers and structural elements in code or text

Code, markdown, or formatting snippets

introduction or conclusion

No Comments

No Known Activations