INDEX

Explanations

references to specific characters and their interactions in a narrative context

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

connecting clauses and phrases

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

Tembelea

-0.58

 EconPapers

-0.56

reathe

-0.52

+#+

-0.48

hoodie

-0.47

 ब्रेकडाउन

-0.47

 AspNetCore

-0.46

 ویکی‌آمباردا

-0.45

ロウィン

-0.43

allocate

-0.42

POSITIVE LOGITS

IsContent

0.46

oč

0.40

getMenuInflater

0.35

makeText

0.35

ItemLayout

0.35

principalColumn

0.34

視

0.34

bootstrapcdn

0.33

⎨

0.33

зулта

0.32

Activations Density 0.041%

references to specific characters and their interactions in a narrative context

connecting clauses and phrases

No Comments

No Known Activations