INDEX

Explanations

suggestive phrases indicating possible causal or correlational relationships in biological contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 sherds

-0.58

 chromosome

-0.57

 caufe

-0.56

 myſelf

-0.55

 verteilt

-0.55

 cauſe

-0.54

istika

-0.54

 negation

-0.53

 ſeveral

-0.53

 ſte

-0.53

POSITIVE LOGITS

 للاسماء

0.78

MENAFN

0.66

ⓧ

0.58

 intended

0.56

 intend

0.56

twimg

0.55

msgTypes

0.54

}*/

0.54

Erreferentziak

0.54

******/

0.54

Activations Density 0.345%

suggestive phrases indicating possible causal or correlational relationships in biological contexts

No Comments

No Known Activations