INDEX

Explanations

phrases related to spacing and distance between objects or components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

torio

-0.47

ीन

-0.47

UrlResolution

-0.44

domo

-0.44

iconCls

-0.43

 LUMP

-0.43

cres

-0.43

Sob

-0.42

oir

-0.42

ijne

-0.42

POSITIVE LOGITS

 spacing

1.33

 distance

1.11

 Spacing

1.10

 Abstand

1.06

 spaced

1.04

 jarak

1.03

 distancia

1.02

 Distance

1.02

 distanza

1.02

spacing

1.00

Activations Density 0.395%

phrases related to spacing and distance between objects or components

No Comments

No Known Activations