INDEX

Explanations

terms related to OAuth authorization processes

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

Code-related tokens, especially after the colon

np_acts-logits-general · gemini-2.0-flash

user identifiers and system scope

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

醐

-0.37

 Hull

-0.34

 anlay

-0.34

 ADMIN

-0.33

 couple

-0.33

ADMIN

-0.32

do

-0.32

”

-0.31

GetCurrent

-0.31

POSITIVE LOGITS

 resourceCulture

0.66

 jsPsych

0.63

verwijspagina

0.62

complexType

0.61

ollectionView

0.61

verifyException

0.60

\{\\

0.59

 Audiodateien

0.58

 Савезне

0.58

 bezeichneter

0.57

Activations Density 0.180%

terms related to OAuth authorization processes

Code-related tokens, especially after the colon

user identifiers and system scope

No Comments

No Known Activations