INDEX

Explanations

possessive pronouns and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

 المعيارى

-1.01

 nahilalakip

-0.85

+:+

-0.79

StructEnd

-0.73

 متعلقه

-0.69

CppMethod

-0.69

 Waray

-0.69

 InputDecoration

-0.68

DockStyle

-0.68

 katal

-0.68

POSITIVE LOGITS

0.53

le

0.52

pageY

0.52

ed

0.49

And

0.49

anium

0.48

0.47

Let

0.47

Activations Density 0.310%

possessive pronouns and relationships

No Comments

No Known Activations