INDEX

Explanations

references to specific parts or sections within a document or text

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kaynağından

-0.57

 استنادى

-0.56

Kariera

-0.51

AnchorTagHelper

-0.51

嘧

-0.49

 Sweet

-0.49

 GenerationType

-0.47

IsMutable

-0.47

ség

-0.45

Sweet

-0.44

POSITIVE LOGITS

BeginContext

0.63

afficheront

0.59

UserScript

0.58

 maupun

0.57

rícula

0.55

 للمعارف

0.55

OCCURRED

0.54

 resourceCulture

0.53

hoea

0.51

 kasarigan

0.50

Activations Density 1.172%

references to specific parts or sections within a document or text

No Comments

No Known Activations