INDEX

Explanations

terms and phrases related to relationship dynamics and challenges

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

tagHelperRunner

-0.52

vorg

-0.51

 vergeten

-0.49

 leerlingen

-0.48

IsContent

-0.48

 Lobby

-0.47

 régle

-0.47

EndContext

-0.46

asso

-0.46

 lokale

-0.46

POSITIVE LOGITS

 dating

0.85

 mutual

0.85

 couples

0.83

 monog

0.82

 marriage

0.79

mergeFrom

0.75

 hurtful

0.75

timacy

0.74

Mutual

0.74

 divorce

0.73

Activations Density 0.374%

terms and phrases related to relationship dynamics and challenges

No Comments

No Known Activations