INDEX

Explanations

references to privacy and confidentiality in personal information

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

Punctuation followed by exception-related words

np_acts-logits-general · gemini-2.0-flash

exceptions and exclusions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 estimés

-0.58

Autoritní

-0.53

 springfox

-0.50

 ultimately

-0.49

GeneratedValue

-0.47

 Overall

-0.47

 nữa

-0.47

 syllables

-0.47

 Catto

-0.46

|}{$

-0.46

POSITIVE LOGITS

 exceptions

1.76

 exception

1.76

 Exceptions

1.75

Exceptions

1.46

 excepción

1.45

exceptions

1.44

except

1.39

 EXCEPT

1.38

 excep

1.38

 except

1.36

Activations Density 0.438%

references to privacy and confidentiality in personal information

Punctuation followed by exception-related words

exceptions and exclusions

No Comments

No Known Activations