INDEX

Explanations

references to specific behaviors or traits associated with individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

verwijspagina

-0.88

 ویکی‌پدیا

-0.76

UnsafeEnabled

-0.65

intios

-0.61

rehension

-0.61

 pinulongan

-0.58

깥

-0.57

 bevis

-0.56

routeProvider

-0.54

dius

-0.54

POSITIVE LOGITS

terday

0.77

YC

0.70

揄

0.68

Yol

0.64

 ớt

0.64

 ymin

0.63

 getY

0.62

YP

0.60

Yat

0.58

YB

0.57

Activations Density 0.332%

references to specific behaviors or traits associated with individuals or groups

No Comments

No Known Activations