INDEX

Explanations

discussions around life, death, and existential concerns

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

Japanese verbs, often followed by particles

np_acts-logits-general · gemini-2.0-flash

tried to do

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

uſ

-0.78

 pleaſure

-0.74

 itſelf

-0.74

دانشنامهٔ

-0.71

 ProtoMessage

-0.70

 themſelves

-0.68

 iſt

-0.68

 ſame

-0.67

 neceſſ

-0.65

 Jefus

-0.65

POSITIVE LOGITS

or

0.54

noaa

0.49

 aient

0.47

verwijspagina

0.47

…

0.47

śl

0.46

यार

0.46

 rather

0.46

,”

0.45

”

0.45

Activations Density 0.047%

discussions around life, death, and existential concerns

Japanese verbs, often followed by particles

tried to do

No Comments

No Known Activations