INDEX

Explanations

terms related to conversion processes, particularly in data and measurements

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

 InputDecoration

-0.76

DebuggerNonUser

-0.68

strum

-0.62

 &___

-0.61

ритори

-0.60

 EconPapers

-0.60

writeFieldEnd

-0.57

 GoogleFonts

-0.56

 يتيمه

-0.56

saraba

-0.55

POSITIVE LOGITS

 Converts

1.33

 converts

1.31

 Convert

1.22

 convert

1.22

 conversions

1.17

 conversion

1.16

 Conversion

1.14

 converting

1.14

 Conversions

1.14

 converter

1.14

Activations Density 0.172%

terms related to conversion processes, particularly in data and measurements

No Comments

No Known Activations