INDEX

Explanations

occurrences of personal achievements or experiences over time

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

during events or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

OGND

-0.50

ListItemIcon

-0.46

TagMode

-0.46

 définiti

-0.46

endphp

-0.46

ậc

-0.45

 prochaines

-0.45

lamabad

-0.45

 HasFactory

-0.45

 tiguan

-0.44

POSITIVE LOGITS

 also

0.49

 during

0.44

 occasionally

0.44

getColumnIndex

0.43

 simultaneously

0.43

 noticed

0.43

CppMethod

0.42

 During

0.41

 notices

0.41

 periodically

0.41

Activations Density 0.044%

occurrences of personal achievements or experiences over time

during events or processes

No Comments

No Known Activations