INDEX

Explanations

expressions related to intertwining or entanglement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

Tikang

-0.58

olg

-0.58

 επί

-0.54

Kuh

-0.51

blit

-0.51

drawImage

-0.51

όν

-0.50

 Ostat

-0.50

Lak

-0.50

SupportActionBar

-0.50

POSITIVE LOGITS

 interwoven

1.15

 tangled

1.13

 intertwined

1.12

 knots

1.09

 weaves

1.09

 weaving

1.08

 intertw

1.08

 woven

1.07

 winding

1.07

 knot

1.06

Activations Density 0.446%

expressions related to intertwining or entanglement

No Comments

No Known Activations