INDEX

Explanations

references to actions, plans, and outcomes, particularly in relational or contrasting contexts

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

Preceding words of prepositions

np_acts-logits-general · gemini-2.0-flash

putting results into context

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

makeText

-0.50



-0.50

 SDLK

-0.47

ografija

-0.46

usercontent

-0.45

tagPool

-0.44

хьтан

-0.43

TagMode

-0.42

WithIOException

-0.42

AnimationsModule

-0.41

POSITIVE LOGITS

 into

0.84

 onto

0.75

 away

0.63

 ואת

0.52

 lên

0.50

 squarely

0.49

 closer

0.48

ไว้

0.47

off

0.46

 nærm

0.45

Activations Density 0.462%

references to actions, plans, and outcomes, particularly in relational or contrasting contexts

Preceding words of prepositions

putting results into context

No Comments

No Known Activations