INDEX

Explanations

requests for assistance or support

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

seeking advice from others

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

numerusform

-0.49

 незавершена

-0.42

WithIOException

-0.41

 finishing

-0.41

 ProtoMessage

-0.40

 Finishing

-0.40

 Савезне

-0.39

 resid

-0.38

setViewportView

-0.38

GRANTED

-0.37

POSITIVE LOGITS

 esperti

0.52

 expertos

0.49

Ҭ

0.47

SuppressLint

0.47

 avoient

0.45

 respondents

0.44

 utafitiHapana

0.44

AndEndTag

0.43

ⓘ

0.42

 étoit

0.41

Activations Density 0.025%

requests for assistance or support

seeking advice from others

No Comments

No Known Activations