INDEX

Explanations

phrases indicating conditions or requirements pertaining to processes or functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Wikimedijinoj

-0.88

最快更新

-0.82

таратура

-0.81

 gynnwys

-0.79

withstanding

-0.77

IANGLES

-0.76

{}'.

-0.74

 beginnetje

-0.74

'%(

-0.73

 سكانية

-0.70

POSITIVE LOGITS

standers

0.54

 springfox

0.52

rogens

0.52

artige

0.51

abord

0.49

 assunto

0.47

gna

0.46

 ello

0.45

кономи

0.45

 niego

0.45

Activations Density 0.411%

phrases indicating conditions or requirements pertaining to processes or functions

No Comments

No Known Activations