INDEX

Explanations

key events, milestones, or official designations within a timeline or context

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

actions beginning or concluding

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

-0.34

 because

-0.32

if

-0.30

%.

-0.30

Ko

-0.29

 becoming

-0.28

HasColumnName

-0.27

ล

-0.27

ang

-0.27

POSITIVE LOGITS

MLLoader

0.84



0.75

 ſei

0.66

OGND

0.66

 تضيفلها

0.65

 好文分享

0.63

<unused8>

0.63

<pad>

0.63

<unused14>

0.62

<unused16>

0.62

Activations Density 0.030%

key events, milestones, or official designations within a timeline or context

actions beginning or concluding

No Comments

No Known Activations