INDEX

Explanations

occurrences of formatting symbols or spacing in the text

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

 للاسماء

-1.09

InjectAttribute

-1.04

Personendaten

-0.97

 EconPapers

-0.95

GEBURTSDATUM

-0.95

InitVars

-0.89

ViewFeatures

-0.89

setVerticalGroup

-0.85

 ویکی‌پدیا

-0.83

 protoimpl

-0.83

POSITIVE LOGITS

fail

0.53

<![

0.49

reeze

0.46

ificación

0.45

 fail

0.43

 nội

0.39

Skal

0.38

 něj

0.37

blick

0.36

rière

0.36

Activations Density 0.249%

occurrences of formatting symbols or spacing in the text

No Comments

No Known Activations