INDEX

Explanations

possessive pronouns and their usage in context

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

written documents and descriptions

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

 zijne

-0.49

 zoude

-0.47

LLocation

-0.45

 lamang

-0.43

 ब्रेकडाउन

-0.43

ExtendWith

-0.43

 tää

-0.42

 ſch

-0.41

 tungkol

-0.41

 dezelve

-0.40

POSITIVE LOGITS

 document

0.59

 script

0.56

 description

0.53

 literature

0.52

 text

0.52

 report

0.51

 diagram

0.50

 brochure

0.50

 article

0.49

 printed

0.49

Activations Density 0.103%

possessive pronouns and their usage in context

written documents and descriptions

No Comments

No Known Activations