INDEX

Explanations

phrases indicating relationships or connections between entities

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

terms following prepositions

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

 Photocase

-0.70

RTEE

-0.63

 NSCoder

-0.63

 Taktlose

-0.60

 Infórmanos

-0.59

SourceChecksum

-0.58

InstrumentedTest

-0.57

Personensuche

-0.56

 <<<<<<<<<<<<<<

-0.56

 Signalez

-0.54

POSITIVE LOGITS

Deb

0.38

 bricolaje

0.36

XMLSchema

0.36

lema

0.35

Pollution

0.35

 Joints

0.35

hithe

0.35

Console

0.35

Activations Density 0.089%

phrases indicating relationships or connections between entities

terms following prepositions

No Comments

No Known Activations