INDEX

Explanations

technical terms and elements within programming and coding contexts

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

Code or markup snippets

np_acts-logits-general · gemini-2.0-flash

citations and code elements

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

</strong>

-0.72

-0.68

$\

-0.63

-0.62

↵↵

-0.62

-0.61

-0.60

<strong>

-0.60

<unused63>

-0.59

POSITIVE LOGITS

 betweenstory

1.77

parsedMessage

1.58

 tartalomajánló

1.56

aarrggbb

1.54

 ExecuteAsync

1.45

AddTagHelper

1.41

########.

1.39

 '\\;'

1.34

ItemBackground

1.33

RenderAtEndOf

1.33

Activations Density 1.698%

technical terms and elements within programming and coding contexts

Code or markup snippets

citations and code elements

No Comments

No Known Activations