INDEX

Explanations

descriptors of time-related qualities and intensities

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

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

retum

-0.59

 AssemblyTitle

-0.53

readValue

-0.52

 ""],

-0.51

meteries

-0.49

imia

-0.48

perma

-0.48

copyOf

-0.48

 former

-0.46

<>();

-0.46

POSITIVE LOGITS

 enough

2.75

enough

2.39

 Enough

2.11

Enough

2.07

 ENOUGH

2.06

 genug

1.97

 genoeg

1.85

 suficiente

1.47

 sufficient

1.36

 demais

1.34

Activations Density 0.239%

descriptors of time-related qualities and intensities

No Comments

No Known Activations