INDEX

Explanations

references to impactful actions and events that lead to significant outcomes

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

adaptiveStyles

-0.51

 recurrir

-0.51

 religieuses

-0.50

PreferredItem

-0.48

 commerciales

-0.47

 internetowa

-0.46

IntoConstraints

-0.45

 huvud

-0.45

PhysRev

-0.44

Personensuche

-0.43

POSITIVE LOGITS

 herself

0.71

TagMode

0.68

تقاوى

0.64

 Pave

0.63

FieldBuilder

0.62

centaje

0.61

themselves

0.61

 собою

0.60

 themselves

0.60

 himself

0.59

Activations Density 0.301%

references to impactful actions and events that lead to significant outcomes

No Comments

No Known Activations