INDEX

Explanations

terms related to drafts and manuscripts in academic or formal writing 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

 OMITBAD

-0.74

]='\

-0.68

glEnable

-0.67

rdoba

-0.67

CloseOperation

-0.66

 Boeh

-0.64

Обе

-0.63

 Amore

-0.62

licenses

-0.62

 Brenner

-0.60

POSITIVE LOGITS

 drafts

1.77

 draft

1.61

 Draft

1.59

 DRAFT

1.58

draft

1.56

Draft

1.54

DRAFT

1.45

 drafted

1.43

DRA

1.40

Dra

1.33

Activations Density 0.101%

terms related to drafts and manuscripts in academic or formal writing contexts

No Comments

No Known Activations