INDEX

Explanations

negations and expressions of logical conditions

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

 não

-0.57

not

-0.55

LOYE

-0.53

no

-0.52

 […]

-0.50

NewLabel

-0.50

 lots

-0.49

 والع

-0.49

The

-0.49

-0.47

POSITIVE LOGITS

 Muck

0.88

 مرئيه

0.84

protoimpl

0.80

httphttps

0.78

GEBURTSDATUM

0.77

AddHtmlAttribute

0.77

 }}"></

0.77

AndEndTag

0.76

 Infór

0.76

enumi

0.75

Activations Density 0.046%

negations and expressions of logical conditions

No Comments

No Known Activations