INDEX

Explanations

time-related phrases or expressions

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

"pass" or time elapsing

np_acts-logits-general · gemini-2.0-flash

time passing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 BoxFit

-0.51

 createState

-0.48

InitVars

-0.46

("}\

-0.43

 BorderLayout

-0.43

IsContent

-0.41

 خارجية

-0.40

makeConstraints

-0.40

ardoor

-0.40

venske

-0.40

POSITIVE LOGITS

 pass

3.59

 passing

3.55

 passes

3.35

 passed

3.26

pass

3.20

 Pass

3.14

passing

3.10

 Passing

3.07

Pass

3.05

Passing

3.03

Activations Density 0.299%

time-related phrases or expressions

"pass" or time elapsing

time passing

No Comments

No Known Activations