INDEX

Explanations

references to awards and recognitions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

WireFormatLite

-0.64

 leaſt

-0.63

KommentareTeilen

-0.58

FormTagHelper

-0.57

CreateModel

-0.57

 trit

-0.56

 FBref

-0.55

.*")]

-0.54

Melo

-0.54

 transférez

-0.53

POSITIVE LOGITS

 award

0.90

 Award

0.82

 awards

0.82

 AWARD

0.73

Award

0.70

 Awards

0.70

Awards

0.68

 prize

0.65

 Prize

0.64

award

0.64

Activations Density 0.119%

references to awards and recognitions in various contexts

No Comments

No Known Activations