INDEX

Explanations

references to specific assembly attributes and programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

urnia

-0.54

nvarchar

-0.49

elung

-0.47

tsburgh

-0.46

legg

-0.46

APORE

-0.44

omla

-0.43

similiano

-0.42

mauer

-0.42

doGet

-0.42

POSITIVE LOGITS

 Views

0.87

Views

0.84

 views

0.80

 view

0.79

 viewpoints

0.76

 VIEW

0.76

 View

0.75

 viewpoint

0.75

 bank

0.73

 judge

0.73

Activations Density 2.732%

references to specific assembly attributes and programming constructs

No Comments

No Known Activations