INDEX

Explanations

discussions about functionality and compatibility issues in software applications

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

error, no, fine, unexpected

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

+#+#

-0.55

rrggbb

-0.49

 MainAxisSize

-0.49

Архівовано

-0.49

帖最后由

-0.48

buttonBar

-0.47

 '\\;'

-0.46

Espèce

-0.45

AutoField

-0.45

orianCalendar

-0.45

POSITIVE LOGITS

sproz

0.38

ERICAL

0.38

 pajero

0.37

 hunne

0.37

 blij

0.37

relief

0.37

chtet

0.36

convex

0.36

 Exacts

0.36

 tunt

0.35

Activations Density 0.080%

discussions about functionality and compatibility issues in software applications

error, no, fine, unexpected

No Comments

No Known Activations