INDEX

Explanations

punctuation and dialog markers

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

Text after an apostrophe

np_acts-logits-general · gemini-2.0-flash

seeing or hearing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

__":

-0.60

ragment

-0.58

我说

-0.58

":

-0.57

TEMPLATES

-0.55

 />";

-0.54

KEYCODE

-0.53

 EINVAL

-0.53

__":

-0.52

 мной

-0.50

POSITIVE LOGITS

 Seeing

0.83

Seeing

0.81

 seeing

0.81

 However

0.79

However

0.78

 although

0.76

 Although

0.75

seeing

0.75

 hearing

0.75

Although

0.75

Activations Density 0.028%

punctuation and dialog markers

Text after an apostrophe

seeing or hearing

No Comments

No Known Activations