INDEX

Explanations

phrases and concepts related to rules and guidelines that impose restrictions or limitations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

Šaltiniai

-0.55

اوم

-0.52

μμα

-0.52

cui

-0.52

itemView

-0.51

 IIRC

-0.50

]^{-

-0.49

rippa

-0.49

 détour

-0.48

harley

-0.48

POSITIVE LOGITS

AutoField

0.72

 ویکی‌پدیای

0.69

expandindo

0.64

ConstraintMaker

0.63

LEncoder

0.61

Autoritní

0.59

 GenerationType

0.59

TagMode

0.59

 insuffisamment

0.58

colhead

0.58

Activations Density 0.534%

phrases and concepts related to rules and guidelines that impose restrictions or limitations

No Comments

No Known Activations