INDEX

Explanations

relationships involving transformations and movements of entities or values

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

庁

-0.51

 Lauf

-0.48

input

-0.47

 input

-0.45

JspWriter

-0.44

 باسم

-0.44

 Públicas

-0.43

 ourselves

-0.43

 aussi

-0.41

 myself

-0.41

POSITIVE LOGITS

makeConstraints

0.69

tvguidetime

0.65

prefixer

0.65

StandardCharsets

0.65

viewDidLoad

0.64

 FetchType

0.62

 Âge

0.61

///</

0.61

DeleteBehavior

0.60

TestBed

0.59

Activations Density 0.356%

relationships involving transformations and movements of entities or values

No Comments

No Known Activations