INDEX

Explanations

references to political affiliations or changes in loyalty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

expandindo

-0.57

 >=",

-0.57

ClientSize

-0.47

 linkovi

-0.47

úrese

-0.47

ArgsConstructor

-0.46

gdala

-0.46

mingen

-0.45

HandleFunc

-0.45

 Paralympic

-0.45

POSITIVE LOGITS

 allegiance

1.31

 loyalty

1.22

 joining

1.21

 loyal

1.13

 join

1.11

 siding

1.10

 aligned

1.10

 joined

1.07

 Joining

1.06

 aligning

1.05

Activations Density 0.626%

references to political affiliations or changes in loyalty

No Comments

No Known Activations