INDEX

Explanations

reasons or justifications for actions or beliefs

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

OOTD

-0.62

ädie

-0.58

elemField

-0.54

enterOuterAlt

-0.53

љено

-0.52

FieldBuilder

-0.52

 OFDb

-0.51

ocities

-0.51

atschappij

-0.50

 Conseils

-0.50

POSITIVE LOGITS

why

0.87

so

0.69

 weshalb

0.69

所以

0.68

why

0.67

ViewFeatures

0.62

 razón

0.60

 razão

0.60

HasForeignKey

0.59

 reason

0.58

Activations Density 0.187%

reasons or justifications for actions or beliefs

No Comments

No Known Activations