INDEX

Explanations

references to institutions, entities, or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

 doInBackground

-0.94

 Réponses

-0.88

 CreateTagHelper

-0.80

 BoxFit

-0.79

 EdgeInsets

-0.78

+#+#

-0.78

 Arzneimit

-0.77

جمعیت

-0.77

PageContext

-0.77

yntaxException

-0.76

POSITIVE LOGITS

Jol

1.01

lllll

1.01

lll

0.97

Kl

0.96

llll

0.95

lul

0.93

llllll

0.93

JL

0.89

CUL

0.88

 thal

0.86

Activations Density 4.339%

references to institutions, entities, or organizations

No Comments

No Known Activations