INDEX

Explanations

terms related to minimizing or optimizing processes, particularly in the context of encoding

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

InjectAttribute

-0.54

:✨

-0.50

 Вікіпе

-0.49

 Chwiliwch

-0.49

 Ел

-0.48

 ساعد

-0.48

met

-0.47

رحلة

-0.47

AddAttribute

-0.47

 NgModule

-0.47

POSITIVE LOGITS

 avoided

1.10

 avoiding

0.97

 avoid

0.96

 Avoidance

0.93

avoid

0.92

 avoidance

0.92

 evit

0.91

 avoids

0.90

 evitar

0.90

 evitando

0.90

Activations Density 0.153%

terms related to minimizing or optimizing processes, particularly in the context of encoding

No Comments

No Known Activations