INDEX

Explanations

negations and phrases that indicate what is not true or desirable

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

Follows "not"

np_acts-logits-general · gemini-2.0-flash

not merely, not just, not only

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

-0.56

<eos>

-0.55

non

-0.49

 without

-0.46

 دون

-0.45

 ellers

-0.44

 senza

-0.43

 werking

-0.43

/^\

-0.41

POSITIVE LOGITS

tagHelperRunner

1.03

SharedDtor

0.99

Personendaten

0.96

 propOrder

0.95

InjectAttribute

0.92

DoubleQuotes

0.89

 Infórmanos

0.87

 Taktlose

0.85

 незавершена

0.85

Activations Density 0.225%

negations and phrases that indicate what is not true or desirable

Follows "not"

not merely, not just, not only

No Comments

No Known Activations