INDEX

Explanations

statements expressing negation or contradiction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 actionMode

-0.53

 ostavi

-0.52

UniformLocation

-0.52

 Vaux

-0.46

انجليز

-0.46

 ويكيميديا

-0.46

 referrerpolicy

-0.45

 recevrez

-0.44

้งาน

-0.44

izd

-0.43

POSITIVE LOGITS

 forget

1.00

 misunderstand

0.88

 worry

0.74

 misunderstood

0.73

 Forget

0.69

 forgetting

0.68

 Donny

0.67

 FetchType

0.66

AnchorStyles

0.65

forget

0.65

Activations Density 0.048%

statements expressing negation or contradiction

No Comments

No Known Activations