INDEX

Explanations

legal and policy-related terminology associated with privacy and terms of service

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

saraba

-0.64

 devrez

-0.61

DebuggerStep

-0.58

QMetaType

-0.56

 comté

-0.56

 StringTokenizer

-0.54

mapreduce

-0.52

avyzd

-0.52

thâu

-0.51

ifstream

-0.51

POSITIVE LOGITS

 footer

0.81

footer

0.74

 onOptions

0.68

 Contact

0.67

 Bourgoin

0.66

 Sitemap

0.66

 Footer

0.66

Kontakt

0.66

Contact

0.65

rawDesc

0.65

Activations Density 0.544%

legal and policy-related terminology associated with privacy and terms of service

No Comments

No Known Activations