INDEX

Explanations

references to source files or data within code

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

"Source" and its variations

np_acts-logits-general · gemini-2.0-flash

source: description or related context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

CPR

-0.42

 anlay

-0.41

Mantenimiento

-0.41

TacToe

-0.40

rupal

-0.39

 MatDialog

-0.38

enumi

-0.37

oliber

-0.36

ements

-0.35

เร็

-0.35

POSITIVE LOGITS

 Source

0.76

 SOURCE

0.71

 getSource

0.69

Source

0.69

 Fonte

0.65

Src

0.61

 Fuente

0.60

complexContent

0.59

 source

0.59

Fonte

0.58

Activations Density 0.190%

references to source files or data within code

"Source" and its variations

source: description or related context

No Known Activations