INDEX

Explanations

references to specific healthcare facilities or institutions

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

Followed by numbers or names

np_acts-logits-general · gemini-2.0-flash

names of people and places

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

 […]

-1.28

…

-0.99

-0.83

...

-0.82

 [...]

-0.75

<eos>

-0.74

[…]

-0.74

-0.73

…

-0.72

-0.71

POSITIVE LOGITS

 Савезне

1.81

Personensuche

1.46

tagHelperRunner

1.41

 pleaſure

1.37

 Мексичка

1.32

:✨

1.32

 Majefty

1.31

 Roskov

1.31

 purpoſe

1.28

ſelves

1.28

Activations Density 0.019%

references to specific healthcare facilities or institutions

Followed by numbers or names

names of people and places

No Comments

No Known Activations