INDEX

Explanations

entities related to a person's background and position within a hierarchical structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 Picchu

-0.56

RegistryLite

-0.55

 insuffisamment

-0.51

 Kigali

-0.50

disposing

-0.49

 насељу

-0.49

 chit

-0.49

 UITableView

-0.49

uitable

-0.49

readystatechange

-0.48

POSITIVE LOGITS

 DELTA

0.60

 AssemblyTitle

0.59

 Delta

0.58

 creeks

0.56

InitVars

0.54

原始内容存档于

0.53

ArgumentParser

0.52

 فريبيس

0.52

 Jurí

0.51

 Moreau

0.51

Activations Density 0.103%

entities related to a person's background and position within a hierarchical structure

No Comments

No Known Activations