INDEX

Explanations

variations of the word "offer."

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

XtraEditors

-0.81

 Gustav

-0.79

Gustav

-0.69

quirrel

-0.69

HandlerContext

-0.66

ientí

-0.66

uously

-0.64

asin

-0.63

alha

-0.63

wachen

-0.62

POSITIVE LOGITS

 Offers

1.91

 offers

1.90

 Offer

1.87

offers

1.84

 offer

1.82

 OFFER

1.77

Offers

1.76

Offer

1.74

 Offering

1.71

offer

1.69

Activations Density 0.050%

variations of the word "offer."

No Comments

No Known Activations