INDEX

Explanations

questions or inquiries that start with the word "Are."

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ftagPool

-0.69

Brainz

-0.66

ilities

-0.62

estacks

-0.61

Condol

-0.57

jsonwebtoken

-0.56

󠁴

-0.56

cesis

-0.55

 consulté

-0.54

 мәкал

-0.54

POSITIVE LOGITS

ⓧ

0.61

 متعلقه

0.59

 }}=\

0.58

Are

0.56

 JTextArea

0.55

&=&\

0.55

Décès

0.55

=[];

0.52

')),

0.52

Are

0.52

Activations Density 0.079%

questions or inquiries that start with the word "Are."

No Comments

No Known Activations