INDEX

Explanations

references to PDF documents and related features

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

</blockquote>

-0.73

-0.70

-0.65

-0.64

 Schofield

-0.64

ThroughAttribute

-0.64

夠

-0.63

con

-0.62

POSITIVE LOGITS

 ſeveral

1.22

 Monfieur

1.17

 Theſe

1.11

 myſelf

1.04

 ―――――

1.04

 faſt

1.03

 pleaſure

1.00

 deſt

0.98

 ſhe

0.98

 Majefty

0.97

Activations Density 0.475%

references to PDF documents and related features

No Comments

No Known Activations