INDEX

Explanations

headers and section titles in a document

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

ans

-0.71

co

-0.70

de

-0.70

to

-0.69

di

-0.68

ir

-0.68

col

-0.67

in

-0.66

or

-0.66

POSITIVE LOGITS

 itſelf

1.32

 juſt

1.20

 greateſt

1.18

 pleaſure

1.17

 ſever

1.16

 myſelf

1.15

 ſmall

1.13

 Diſ

1.12

 leſs

1.11

 deſt

1.11

Activations Density 0.065%

headers and section titles in a document

No Comments

No Known Activations