INDEX

Explanations

programming constructs related to loops and conditions in code

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

code structure and iteration

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 ujednoznacz

-0.60

 "..\..\..\

-0.59

dataclass

-0.59

tvguidetime

-0.58

OrNil

-0.57

存于互联网档案馆

-0.55

 "..\..\

-0.54

acquired

-0.54

 незавершена

-0.52

 ProtoMessage

-0.52

POSITIVE LOGITS

ContentAsync

0.36

 COVID

0.32

 torebka

0.30

 tamp

0.29

 Covid

0.29

outSlope

0.28

Populate

0.28

 säkert

0.27

 Colombie

0.27

 ägg

0.26

Activations Density 0.004%

programming constructs related to loops and conditions in code

code structure and iteration

No Comments

No Known Activations