INDEX

Explanations

terms related to shadows and shadow-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-0.51

dat

-0.51

 involved

-0.50

The

-0.49

One

-0.48

ParseTree

-0.47

 coinvol

-0.47

Hi

-0.47

as

-0.47

 terlibat

-0.47

POSITIVE LOGITS

mybatisplus

0.98

adaptiveStyles

0.93

upply

0.89

supply

0.87

 Bourgoin

0.86

 supply

0.86

AddTagHelper

0.84

 propOrder

0.81

SUPPLY

0.81

 SUPPLY

0.80

Activations Density 0.107%

terms related to shadows and shadow-related concepts

No Comments

No Known Activations