INDEX

Explanations

references to documents or identity verification processes

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

Japanese words followed by particles/grammar

np_acts-logits-general · gemini-2.0-flash

time, people, things, day

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-1.46

-1.41

-1.22

in

-1.22

-1.19

-1.17

-1.13

and

-1.12

to

-1.09

as

-1.08

POSITIVE LOGITS

 myſelf

2.69

 itſelf

2.56

Efq

2.53

 ―――――

2.49

 photolibrary

2.46

 Monfieur

2.46

 Majefty

2.41

 Reſ

2.38

 Anſ

2.36

 Houſe

2.36

Activations Density 0.320%

references to documents or identity verification processes

Japanese words followed by particles/grammar

time, people, things, day

No Comments

No Known Activations