INDEX

Explanations

words reflecting personal relationships and emotional connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 unavailable

-0.65

absent

-0.60

 impossible

-0.57

 unseen

-0.57

 Absent

-0.54

 absent

-0.53

 impossibility

-0.50

 lacked

-0.49

 Impossible

-0.48

 unthinkable

-0.48

POSITIVE LOGITS

 doesn

1.61

doesn

1.40

 Doesn

1.39

 does

1.39

Does

1.29

don

1.29

 Does

1.28

does

1.27

Doesn

1.27

 doesnt

1.24

Activations Density 0.228%

words reflecting personal relationships and emotional connections

No Comments

No Known Activations