INDEX

Explanations

elements related to JSON data structures

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

`<start_of_turn>` followed by `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

 econó

-0.46

 financially

-0.42

 vejo

-0.42

guenos

-0.40

 escaleras

-0.40

 jäsen

-0.39

 geladeira

-0.39

 vähän

-0.38

 forças

-0.38

 myö

-0.38

POSITIVE LOGITS

parsedMessage

0.62

 nakalista

0.58

VersionUID

0.57

HostException

0.53

Chham

0.49

RectangleBorder

0.49

RTSN

0.48

DockStyle

0.48

 betweenstory

0.45

AppMethodBeat

0.45

Activations Density 0.026%

elements related to JSON data structures

`<start_of_turn>` followed by `user`

No Comments

No Known Activations