INDEX

Explanations

terms related to the extent or degree of various phenomena

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

complexContent

-0.91

 виправивши

-0.85

دانشنامهٔ

-0.76

Revenir

-0.76

::_('

-0.73

 MatDialog

-0.73

 intptr

-0.72

tonsoft

-0.71

__(/*!

-0.71

GEBURTSDATUM

-0.71

POSITIVE LOGITS

 auquel

0.52

 nature

0.51

 exacte

0.48

var

0.46

 waarmee

0.45

 vary

0.43

 waarin

0.43

 extent

0.43

 varies

0.43

fficio

0.43

Activations Density 0.561%

terms related to the extent or degree of various phenomena

No Comments

No Known Activations