INDEX

Explanations

references to proximity or location

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

near to something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

getMenuInflater

-0.40

だけの

-0.34

 StringVar

-0.34

 entirety

-0.33

fromLTRB

-0.33

StringWriter

-0.32

 disulfide

-0.32

hasOwnProperty

-0.31

AddWithValue

-0.31

 jsonObj

-0.30

POSITIVE LOGITS

 near

1.22

near

1.21

Near

1.20

 Near

1.16

 NEAR

1.09

NEAR

0.98

 nær

0.92

 dekat

0.88

 возле

0.87

nearby

0.87

Activations Density 0.020%

references to proximity or location

near to something

No Comments

No Known Activations