INDEX

Explanations

questions and statements about technology and troubleshooting

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

how to ask a question

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

 contextLoads

-0.70

Demikian

-0.49

^(@

-0.49

ruik

-0.48

 facult

-0.45

SaveChangesAsync

-0.45

Népesség

-0.45

frontmatter

-0.43

Artik

-0.43

iastical

-0.43

POSITIVE LOGITS

TypedDataSet

0.53

GEBURTSDATUM

0.50

 ProtoMessage

0.50

MessageOf

0.47

0.46

ScopeManager

0.46

 noDo

0.45

IsContent

0.45

outState

0.44

AddTagHelper

0.43

Activations Density 0.001%

questions and statements about technology and troubleshooting

how to ask a question

No Comments

No Known Activations