INDEX

Explanations

similarities and comparisons in language

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

like comparisons to others

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

expandindo

-0.47

endphp

-0.45

AccessorTable

-0.44

ereal

-0.42

 للمعارف

-0.41

 ensi

-0.40

 marvellous

-0.40

cookieParser

-0.39

cenzo

-0.39

izielle

-0.39

POSITIVE LOGITS

 like

0.64

antMatchers

0.55

Like

0.54

 unlike

0.53

like

0.50

 liksom

0.50

 όπως

0.50

 Like

0.50

เช่น

0.49

 seperti

0.48

Activations Density 0.020%

similarities and comparisons in language

like comparisons to others

No Comments

No Known Activations

similarities and comparisons in language

like comparisons to others

No Comments

No Known Activations