INDEX

Explanations

expressions related to emotions and perceptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 silent

-0.50

caris

-0.47

addContainerGap

-0.46

nown

-0.45

rstrip

-0.44

//{

-0.43

rüstung

-0.43

xas

-0.43

 Haupt

-0.43

美子

-0.43

POSITIVE LOGITS

 SENSE

0.93

 Sense

0.89

sense

0.82

 humour

0.81

 propOrder

0.80

 calendriers

0.77

ChildScrollView

0.77

 sense

0.76

 humor

0.75

Sense

0.74

Activations Density 0.078%

expressions related to emotions and perceptions

No Comments

No Known Activations