INDEX

Explanations

terms and phrases related to separating entities or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

ⓧ

-0.61

/*

-0.59

AndEndTag

-0.58

wapV

-0.57

formaz

-0.53

Tikang

-0.52

LLocation

-0.52

ähkö

-0.51

DebuggerStep

-0.50

равда

-0.49

POSITIVE LOGITS

 separate

3.06

separate

2.76

 Separate

2.72

Separate

2.67

 seperate

2.60

 separately

2.58

 SEPAR

2.54

 independent

2.29

 separat

2.24

 Separ

2.15

Activations Density 0.862%

terms and phrases related to separating entities or concepts

No Comments

No Known Activations