INDEX

Explanations

notable markers or indicators that signify the start of significant content or sections in a document

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

Followed by letters

np_acts-logits-general · gemini-2.0-flash

upper, top, fen, 5, c, o, ct

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

 Roskov

-1.14

MigrationBuilder

-1.08

 صوتيه

-1.07

 الحره

-1.04

httphttps

-1.04

polation

-1.03

SharedDtor

-1.03

 المعيارى

-0.99

 ComVisible

-0.97

CloseOperation

-0.97

POSITIVE LOGITS

te

0.63

es

0.61

ch

0.59

ss

0.58

0.57

ain

0.57

0.55

0.54

ien

0.54

Activations Density 0.633%

notable markers or indicators that signify the start of significant content or sections in a document

Followed by letters

upper, top, fen, 5, c, o, ct

No Comments

No Known Activations