INDEX

Explanations

terms related to molecular weight and molecular structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

InSection

-0.79

 Heiden

-0.71

 InputDecoration

-0.69

ennai

-0.60

 hjäl

-0.58

 Argus

-0.57

 Chron

-0.56

 Gerhard

-0.56

Nop

-0.55

sibilidad

-0.55

POSITIVE LOGITS

 molecules

1.91

 Molecules

1.83

 molecular

1.70

molecules

1.65

molecular

1.62

 molecule

1.61

 Molecular

1.51

 Molecule

1.50

Mole

1.42

molecule

1.41

Activations Density 0.302%

terms related to molecular weight and molecular structures

No Comments

No Known Activations