INDEX

Explanations

terminators or indicators denoting the end of content segments or files

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

EOF EOL END delimiters

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

 createState

-0.46

verwijspagina

-0.45

MutableLiveData

-0.44

mRecyclerView

-0.44

ConstraintMaker

-0.42

RefreshLayout

-0.41

 inner

-0.41

ngrx

-0.40

 ArrayAdapter

-0.40

 still

-0.40

POSITIVE LOGITS

EOF

0.93

EOF

0.84

 <<<<<<<<<<<<<<

0.59

eof

0.52

 oprot

0.51

EOD

0.48

EOT

0.47

 HttpNotFound

0.46

ьаж

0.46

 NUKAT

0.45

Activations Density 0.001%

terminators or indicators denoting the end of content segments or files

EOF EOL END delimiters

No Comments

No Known Activations