INDEX

Explanations

references to attribution and credit 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 @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 raya

-0.50

ecuted

-0.48

 around

-0.47

 paik

-0.47

around

-0.47

 rundt

-0.45

∨

-0.44

 suiv

-0.43

 Manip

-0.43

 thuyết

-0.41

POSITIVE LOGITS

owe

0.83

 attribution

0.82

 owes

0.81

protoimpl

0.77

TestingModule

0.74

 समीक्षक

0.72

 محفوظة

0.72

 owed

0.70

Autoritní

0.69

gave

0.68

Activations Density 0.334%

references to attribution and credit in various contexts

No Comments

No Known Activations