INDEX

Explanations

references to websites or web-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

er

-0.94

 Gentry

-0.77

tr

-0.73

ber

-0.71

ran

-0.67

sub

-0.67

ah

-0.67

erle

-0.65

bin

-0.64

 urbaine

-0.63

POSITIVE LOGITS

 Website

1.20

googleapis

1.19

 Websites

1.18

 websites

1.18

WEBSITE

1.17

websites

1.15

 website

1.10

Websites

1.09

website

1.09

Website

1.08

Activations Density 0.069%

references to websites or web-related content

No Comments

No Known Activations