INDEX

Explanations

phrases discussing the concepts of loss and generality in various contexts

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

TagHelpers

-0.50

 Kooper

-0.49

authenticate

-0.46

RuleContext

-0.46

uchtung

-0.45

 AssemblyProduct

-0.45

CppMethod

-0.44

 jadx

-0.44

jspx

-0.44

acherous

-0.44

POSITIVE LOGITS

 loss

2.61

 lost

2.40

Loss

2.23

 Loss

2.21

loss

2.20

 losses

2.17

 LOSS

2.08

 loses

1.95

lost

1.94

LOSS

1.93

Activations Density 0.522%

phrases discussing the concepts of loss and generality in various contexts

No Comments

No Known Activations