INDEX

Explanations

references to various kings and monarchs

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

 Whistler

-0.66

 Zacks

-0.58

PickerController

-0.58

CloseOperation

-0.57

 Hawke

-0.57

 Travis

-0.56

indicato

-0.56

UrlResolution

-0.55

älä

-0.53

AddTagHelper

-0.52

POSITIVE LOGITS

 King

1.07

 Kings

1.06

 KING

1.00

 kings

0.97

 king

0.92

King

0.90

Kings

0.89

 Queen

0.85

 Koenig

0.84

👑

0.81

Activations Density 0.107%

references to various kings and monarchs

No Comments

No Known Activations