INDEX

Explanations

determiners and quantifiers in various contexts

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

 admittedly

-0.61

 Paglinawan

-0.61

 ostensibly

-0.59

miyorum

-0.52

 impri

-0.52

 decidedly

-0.51

 pared

-0.50

 comuniques

-0.50

nocześnie

-0.50

joueurs

-0.50

POSITIVE LOGITS

 stuff

0.65

 advices

0.65

 legislation

0.64

 matured

0.64

styleType

0.61

 Legislation

0.61

 stuffs

0.61

AutoScale

0.60

Legislation

0.60

++];

0.58

Activations Density 0.346%

determiners and quantifiers in various contexts

No Comments

No Known Activations