INDEX

Explanations

phrases related to structural or functional comparisons in systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

sidemargin

-0.73

fromnode

-0.66

Ữ

-0.65

RefNanny

-0.64

titleMargin

-0.63

orianCalendar

-0.62

FieldNumber

-0.61

parsedMessage

-0.61

ApiModelProperty

-0.57

TextAppearance

-0.57

POSITIVE LOGITS

 split

0.74

 splitting

0.73

 multi

0.71

 single

0.71

Split

0.67

 splits

0.66

 Split

0.66

 múltiple

0.60

multi

0.58

Multi

0.58

Activations Density 1.194%

phrases related to structural or functional comparisons in systems

No Comments

No Known Activations