INDEX

Explanations

functions and commands related to generating and manipulating HTML content

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

Code snippets or code-related text

np_acts-logits-general · gemini-2.0-flash

html 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 propOrder

-0.84

 Wicidata

-0.70

Koordinaten

-0.68

 BoxFit

-0.67

 respald

-0.66

 onCancelled

-0.66

entibus

-0.66

 ContentValues

-0.66

AxisAlignment

-0.65

 ansik

-0.64

POSITIVE LOGITS

'<

1.26

"<

1.23

'<

1.14

"<

1.03

("<

0.97

('<

0.96

`<

0.83

}<

0.81

`<

0.81

Activations Density 0.066%

functions and commands related to generating and manipulating HTML content

Code snippets or code-related text

html and code elements

No Comments

No Known Activations