INDEX

Explanations

instances of the word "show" and its variations in different contexts

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

"show" followed by various prepositions

np_acts-logits-general · gemini-2.0-flash

show off or show how

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 utilitarian

-0.52

terape

-0.52

 Norbert

-0.50

DPD

-0.47

 Baltic

-0.47

bati

-0.46

pherals

-0.44

 cylindrical

-0.44

 Mortimer

-0.44

 libc

-0.44

POSITIVE LOGITS

show

1.32

 Show

1.30

Show

1.27

 show

1.20

 Shows

1.19

 SHOW

1.14

shows

1.13

Shows

1.12

SHOW

1.09

 Showing

1.03

Activations Density 0.119%

instances of the word "show" and its variations in different contexts

"show" followed by various prepositions

show off or show how

No Comments

No Known Activations