INDEX

Explanations

technical terms related to data structure and visualization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

nodoc

-0.52

forChild

-0.47

Geplaatst

-0.46

Хьажоргаш

-0.43

orkin

-0.42

 kasarigan

-0.41

endsection

-0.40

featureID

-0.39

ifrance

-0.38

μφωνα

-0.38

POSITIVE LOGITS

 blue

2.25

 yellow

2.16

 purple

2.06

 green

2.01

 white

1.96

blue

1.95

 pink

1.92

 grey

1.90

red

1.90

 gray

1.89

Activations Density 2.915%

technical terms related to data structure and visualization

No Comments

No Known Activations