INDEX

Explanations

references to opinions, feelings, and subjective assessments

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

that followed by specific words

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

RenderAtEndOf

-0.61

complexContent

-0.61

ftagPool

-0.53

➌

-0.52

 FetchType

-0.51

EndContext

-0.50

 CURIAM

-0.50

Rptr

-0.50

 ویکی‌پدی

-0.49

Географиясе

-0.49

POSITIVE LOGITS

berdayakan

0.44

ambilan

0.41

 orejas

0.40

 conmigo

0.40

jarkan

0.39

rektur

0.38

 vengan

0.38

ticias

0.38

وردار

0.38

 desnuda

0.38

Activations Density 0.063%

references to opinions, feelings, and subjective assessments

that followed by specific words

No Comments

No Known Activations