INDEX

Explanations

tokens related to HTTP request headers and environment variables

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

Strings within brackets or parentheses

np_acts-logits-general · gemini-2.0-flash

http headers

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

 Audiodateien

-0.89

OGND

-0.82

DoubleQuotes

-0.72

tvguidetime

-0.70

InputBorder

-0.68

FieldBuilder

-0.66

abestanden

-0.65

ValueStyle

-0.64

 wireType

-0.64

titian

-0.63

POSITIVE LOGITS

__

0.61

"__

0.60

__

0.58

___

0.57

'__

0.51

 salg

0.51

____

0.46

agus

0.45

彿

0.45

ucas

0.45

Activations Density 0.258%

tokens related to HTTP request headers and environment variables

Strings within brackets or parentheses

http headers

No Comments

No Known Activations