INDEX

Explanations

structured data attributes and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

//

-0.54

 '\\;'

-0.52

Obrázky

-0.46

 jantar

-0.46

postgresql

-0.45

ография

-0.44

entant

-0.43

שלום

-0.43

 kont

-0.43

 compro

-0.43

POSITIVE LOGITS

ScopeManager

0.60

ArgsConstructor

0.58

adpleegd

0.57

esez

0.55

AlterField

0.55

èvent

0.54

expandindo

0.53

TagHelper

0.52

новниш

0.51

CreateMap

0.50

Activations Density 0.310%

structured data attributes and references

No Comments

No Known Activations