INDEX

Explanations

terms related to processes of extraction, collection, and removal

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

following "from"

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 >=",

-0.43

 للاسماء

-0.41

 Incoming

-0.40

colgroup

-0.40

RTLI

-0.40

demies

-0.40

NewLabel

-0.39

DMETHOD

-0.39

 TextAppearance

-0.39

ListItemIcon

-0.39

POSITIVE LOGITS

 from

1.81

from

1.30

 FROM

1.17

 kutoka

1.15

จาก

1.15

 dari

1.13

 från

1.13

 therefrom

1.13

 từ

1.10

从

1.09

Activations Density 0.655%

terms related to processes of extraction, collection, and removal

following "from"

No Comments

No Known Activations