INDEX

Explanations

references to programming concepts or keywords

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

<start_of_turn>user

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

Билгалдахарш

-0.41

 termica

-0.39

MemoryWarning

-0.39

 crossorigin

-0.36

 rijden

-0.36

 auguri

-0.36

 vergeten

-0.36

bajo

-0.35

 ziekte

-0.35

POSITIVE LOGITS

RegressionTest

0.50

 mergeFrom

0.49

msgTypes

0.47

enterOuterAlt

0.44

Gön

0.43

Hentet

0.43

Portály

0.43

épendance

0.42

writeFieldEnd

0.41

NameInMap

0.41

Activations Density 0.000%

references to programming concepts or keywords

<start_of_turn>user

No Comments

No Known Activations