INDEX

Explanations

terms related to leadership or organizational roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 AssemblyCulture

-0.60

 Ratu

-0.46

phosa

-0.45

Oyo

-0.43

 decir

-0.42

 Embaj

-0.42

cupertino

-0.41

Tikang

-0.40

 Lovato

-0.40

 Tinubu

-0.40

POSITIVE LOGITS

Халык

0.74

เหร

0.72

isielt

0.72

Efq

0.72

UnusedPrivate

0.71

ogonal

0.71

 "','

0.70

extAlignment

0.69

sizeCache

0.69

irited

0.68

Activations Density 0.137%

terms related to leadership or organizational roles

No Comments

No Known Activations