INDEX

Explanations

terms related to conversion processes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 numberWith

-0.58

-0.51

 GoogleFonts

-0.49

 InputDecoration

-0.49

uría

-0.48

 MenuView

-0.47

zionata

-0.47

 partenza

-0.47

ようになった

-0.47

new

-0.46

POSITIVE LOGITS

 Converts

1.12

 Conversions

0.96

 converts

0.95

 converters

0.92

 conversions

0.90

 converter

0.88

 Converting

0.86

 Convert

0.85

 Converter

0.84

ToInt

0.82

Activations Density 0.120%

terms related to conversion processes in various contexts

No Comments

No Known Activations