INDEX

Explanations

desires and intentions expressed through the word "want."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

Kini

-0.73

 hindurch

-0.70

 ранее

-0.63

FormTagHelper

-0.62

 inference

-0.62

Autoritní

-0.62

 méret

-0.62

บริการ

-0.61

 Alternatively

-0.60

 NDEBUG

-0.60

POSITIVE LOGITS

 want

0.98

 wants

0.87

 wanted

0.84

 must

0.72

 wanna

0.71

 always

0.65

Give

0.64

 quiero

0.64

 should

0.64

 sure

0.63

Activations Density 0.160%

desires and intentions expressed through the word "want."

No Comments

No Known Activations