INDEX

Explanations

words related to connections 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 @ 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

or

-0.49

 Brasileiro

-0.45

-0.44

ječ

-0.44

чих

-0.43

-0.42

-0.41

大

-0.41

וצ

-0.41

POSITIVE LOGITS

tvguidetime

0.96

modelBuilder

0.95

تقاوى

0.93

tagHelperRunner

0.93

WebServlet

0.90

XmlType

0.88

complexContent

0.86

AutoresizingMask

0.85

DockStyle

0.85

&=&

0.85

Activations Density 0.288%

words related to connections and relationships

No Comments

No Known Activations