INDEX

Explanations

instances of the word "on."

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

"On" followed by an article

np_acts-logits-general · gemini-2.0-flash

on followed by articles/determiners

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

 gynnwys

-0.78

begle

-0.50

standers

-0.49

 iné

-0.47

riebenen

-0.46

 inbox

-0.46

ために

-0.46

全文

-0.45

 Infórmanos

-0.44

 què

-0.44

POSITIVE LOGITS

PerformLayout

0.80

 MainAxisSize

0.74

 оригіналу

0.71

ViewImports

0.69

 CURIAM

0.65

findpost

0.62

stdc

0.61

EndContext

0.59

DeleteBehavior

0.58

PostExecute

0.57

Activations Density 0.198%

instances of the word "on."

"On" followed by an article

on followed by articles/determiners

No Comments

No Known Activations