INDEX

Explanations

technical jargon and descriptors related to complex structures and analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

InstanceOf

-0.49

тру

-0.49

 sauf

-0.47

ụp

-0.47

 desgra

-0.47

 acorde

-0.46

nelse

-0.45

AnchorTagHelper

-0.45

 odpowied

-0.45

migrationBuilder

-0.44

POSITIVE LOGITS

xffffffff

0.70

 complex

0.69

 betreft

0.68

 complexities

0.67

 utford

0.65

complex

0.65

NameInMap

0.64

 compless

0.64

 environments

0.61

Complexity

0.60

Activations Density 0.621%

technical jargon and descriptors related to complex structures and analysis

No Comments

No Known Activations