INDEX

Explanations

instances of location or context-related phrases

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

in followed by word

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

 Insel

-0.48

tip

-0.47

-0.46

beeren

-0.45

us

-0.45

it

-0.45

containsKey

-0.44

<i>

-0.44

POSITIVE LOGITS

SPATH

0.71

ต่างๆ

0.71

 Diſ

0.69

 فريبيس

0.69

 pleaſure

0.68

ANDOM

0.66

olesale

0.66

 saites

0.66

 faſt

0.65

 Houſe

0.65

Activations Density 0.160%

instances of location or context-related phrases

in followed by word

No Comments

No Known Activations