INDEX

Explanations

references to specific individuals or names

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

Token "W" followed by specific characters

np_acts-logits-general · gemini-2.0-flash

starting 'W'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

IsContent

-0.85

Pautan

-0.64

 незавершена

-0.62

IDTH

-0.58

ContentAsync

-0.57

ConstraintMaker

-0.55

 EconPapers

-0.54

 <=",

-0.53

Kus

-0.52

ViewImports

-0.52

POSITIVE LOGITS

eren

0.56

RUnlock

0.53

 BrowserModule

0.53

észet

0.49

rest

0.49

 independencia

0.49

seln

0.48

edded

0.47

 ILogger

0.47

anton

0.47

Activations Density 0.250%

references to specific individuals or names

Token "W" followed by specific characters

starting 'W'

No Comments

No Known Activations