INDEX

Explanations

mathematical expressions and conclusions within a formal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

󠁿

-0.57

TagHelper

-0.56

 Hatton

-0.55

Clik

-0.55

 CascadeType

-0.55

]._

-0.54

 lenker

-0.53

циональный

-0.53

rrggbb

-0.53

Хьажоргаш

-0.53

POSITIVE LOGITS

RegressionTest

0.77

TagMode

0.63

 通販

0.61

 Thus

0.58

TestingModule

0.58

PostMapping

0.56

 therefore

0.56

 Therefore

0.56

MLLoader

0.55

 thus

0.55

Activations Density 0.717%

mathematical expressions and conclusions within a formal context

No Comments

No Known Activations