INDEX

Explanations

assertions and negations about events or states of being

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

Sentences starting with "That's" or "'That's"

np_acts-logits-general · gemini-2.0-flash

that is followed by explanation

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

SequentialGroup

-0.73

الدراسه

-0.70

 ModelExpression

-0.64

BorderFactory

-0.57

 HttpHeaders

-0.56

--){

-0.54

Bioaccumulative

-0.54

simov

-0.53

География

-0.53

 Aene

-0.50

POSITIVE LOGITS

why

1.01

how

0.96

 where

0.82

 what

0.80

 exactly

0.62

 fine

0.61

 because

0.60

why

0.60

 aside

0.58

 besides

0.57

Activations Density 0.083%

assertions and negations about events or states of being

Sentences starting with "That's" or "'That's"

that is followed by explanation

No Comments

No Known Activations