INDEX

Explanations

references to vice presidential roles or positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

setObjectName

-0.56

attes

-0.53

 giovan

-0.51

 updateUser

-0.50

 Patch

-0.50

aining

-0.50

 ditu

-0.50

hamcrest

-0.49

++);

-0.48

upun

-0.48

POSITIVE LOGITS

 president

1.10

 presidents

1.08

 President

1.06

President

0.96

 Presidents

0.96

 versa

0.92

 PRESIDENT

0.86

president

0.86

PRESIDENT

0.83

Presidents

0.83

Activations Density 0.094%

references to vice presidential roles or positions

No Comments

No Known Activations