INDEX

Explanations

comments and annotations in code

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CloseOperation

-0.65

 שוליים

-0.61

Autoritní

-0.55

 pinulongan

-0.55

Vidite

-0.54

]")]

-0.54

ThroughAttribute

-0.53

exitRule

-0.52

AutoScale

-0.51

rungsseite

-0.51

POSITIVE LOGITS

rimid

0.37

SequentialGroup

0.36

numerusform

0.35

 conclusion

0.34

 dite

0.34

 pith

0.33

umab

0.32

ideen

0.32

equiv

0.32

님

0.32

Activations Density 0.003%

comments and annotations in code

No Comments

No Known Activations