INDEX

Explanations

mentions of innovation 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Monfieur

-1.21

 pleaſure

-1.16

 ſeveral

-1.16

Efq

-1.15

 Theſe

-1.14

 myſelf

-1.13

 Houſe

-1.10

SequentialGroup

-1.09

 Diſ

-1.08

berdayakan

-1.07

POSITIVE LOGITS

 invented

0.69

 invent

0.68

des

0.62

0.59

↵↵

0.59

 modern

0.59

 innovations

0.58

 innovation

0.54

 inven

0.54

en

0.53

Activations Density 0.104%

mentions of innovation in various contexts

No Comments

No Known Activations