INDEX

Explanations

symbols and punctuation marks that indicate changes in data or versioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Савезне

-1.08

addCriterion

-0.97

 parseFrom

-0.87

Rhestr

-0.86

Билгалдахарш

-0.86

CopyWith

-0.84

webElementXpaths

-0.84

GEBURTSDATUM

-0.80

脚注の使い方

-0.80

IContainer

-0.79

POSITIVE LOGITS

✭✭

0.64

 means

0.50

adás

0.47

Seb

0.46

su

0.45

Redire

0.43

وير

0.42

kunta

0.42

und

0.41

Activations Density 0.232%

symbols and punctuation marks that indicate changes in data or versioning

No Comments

No Known Activations