INDEX

Explanations

terms related to workflow processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

mybatisplus

-0.92

ます

-0.79

 fatt

-0.77

 hyperplasia

-0.77

########.

-0.74

 Neustadt

-0.72

 Shanks

-0.71

 ATTR

-0.69

ParseException

-0.69

INCLUDE

-0.68

POSITIVE LOGITS

 Workflow

1.38

Workflow

1.36

 workflow

1.28

workflow

1.25

 workflows

1.20

WF

0.97

verwijspagina

0.84

(!__

0.83

wf

0.81

WF

0.81

Activations Density 0.026%

terms related to workflow processes

No Comments

No Known Activations