INDEX

Explanations

symbols indicating shifts in data or code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

-0.55

fre

-0.54

Fre

-0.51

Fre

-0.51

-0.50

’

-0.49

NG

-0.48

POSITIVE LOGITS

<<=

1.15

AddTagHelper

1.12

CloseOperation

0.96

 AssemblyCompany

0.92

InjectAttribute

0.91

ValueStyle

0.89

تقاوى

0.86

]<<

0.84

enterOuterAlt

0.84

 tartalomajánló

0.84

Activations Density 0.021%

symbols indicating shifts in data or code

No Comments

No Known Activations

symbols indicating shifts in data or code

No Comments

No Known Activations