INDEX

Explanations

Nouns related to significant entities, particularly those that denote importance or relevance in the context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 Finally

-0.55

 BigNumber

-0.51

 finally

-0.50

LayoutConstraint

-0.49

Recap

-0.49

InputTagHelper

-0.48

出版年

-0.47

 doings

-0.46

orescence

-0.46

ajur

-0.46

POSITIVE LOGITS

 referenties

0.81

batore

0.78

oredCriteria

0.72

 inspiração

0.68

 inspiration

0.66

UnusedPrivate

0.64

 linkovi

0.64

twimg

0.63

 fallu

0.63

padded

0.62

Activations Density 0.228%

Nouns related to significant entities, particularly those that denote importance or relevance in the context

No Comments

No Known Activations