INDEX

Explanations

references to statistics and information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

RAG

-0.85

cination

-0.85

REA

-0.85

'}>

-0.84

*/

-0.83

ciaż

-0.83

parsedMessage

-0.80

nasi

-0.74

⎯

-0.74

RAG

-0.74

POSITIVE LOGITS

 veggies

1.31

 meds

1.27

 govt

1.26

 stats

1.23

 info

1.22

 carbs

1.19

 Govt

1.16

 kids

1.11

 Dept

1.11

Govt

1.11

Activations Density 0.126%

references to statistics and information

No Comments

No Known Activations