INDEX

Explanations

phrases that express possibilities and inquiries related to anyone or anything

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

endphp

-0.71

 <<<<<<<<<<<<<<

-0.70

riwal

-0.65

PerformLayout

-0.64

GraphicsUnit

-0.62

 CURIAM

-0.60

parsedMessage

-0.60

KeySpec

-0.59

 "..\..\..\

-0.58

 للمعارف

-0.58

POSITIVE LOGITS

 Anyone

1.06

 anyone

1.04

 Anybody

1.01

anyone

1.00

Any

0.99

 anybody

0.98

Any

0.98

Anyone

0.98

any

0.93

Anybody

0.91

Activations Density 0.096%

phrases that express possibilities and inquiries related to anyone or anything

No Comments

No Known Activations