INDEX

Explanations

patterns or structures in textual data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 betweenstory

-1.14

GEBURTSDATUM

-1.07

expandindo

-0.90

IVEREF

-0.83

 kaarangay

-0.82

ThemeOverlay

-0.82

AutoScaleMode

-0.81

 beginnetje

-0.77

 jsPsych

-0.77

دانشنامهٔ

-0.76

POSITIVE LOGITS

帖最后由

0.57

ToScroll

0.55

SupportActionBar

0.54

Примечания

0.51

BindingResult

0.50

RenderAtEndOf

0.46

CompleteListener

0.45

 ModelAndView

0.44

 οποίο

0.43

0.42

Activations Density 0.096%

patterns or structures in textual data

No Comments

No Known Activations