INDEX

Explanations

numerical values, particularly related to contact information or timestamps

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

dates and numbers

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 <<<<<<<<<<<<<<

-0.54

 captains

-0.51

AddTagHelper

-0.50

rrggbb

-0.50

 abra

-0.49

 समीक्षक

-0.47

 analogues

-0.46

AccessorTable

-0.46

étit

-0.45

رشف

-0.44

POSITIVE LOGITS

ंदीखरीदारी

0.48

 informée

0.42

zeß

0.36

 utafitiHapana

0.35

enumi

0.35

libft

0.34

 allAfrica

0.31

RTSN

0.31

 porém

0.30

 palk

0.30

Activations Density 0.130%

numerical values, particularly related to contact information or timestamps

dates and numbers

No Comments

No Known Activations