INDEX

Explanations

references to names, entities, or important terms within various contexts

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

parsedMessage

-0.60

uxxxx

-0.59

!*\

-0.58

 fieldNum

-0.55

OGND

-0.54

Diwedd

-0.52

 незавершена

-0.52

koľvek

-0.51

ineno

-0.51

 تضيفلها

-0.51

POSITIVE LOGITS

fromnode

0.75

ModelSerializer

0.70

ükemmel

0.53

 onCreateView

0.51

httphttps

0.50

audiovisuel

0.49

 pstmt

0.48

stretchr

0.48

PullParser

0.48

 quadrangle

0.48

Activations Density 0.812%

references to names, entities, or important terms within various contexts

No Comments

No Known Activations