INDEX

Explanations

references to leadership roles and positions within organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ercito

-0.51

 Autorizaciones

-0.50

BufferException

-0.50

 Neale

-0.49

 primitives

-0.47

perten

-0.47

ymas

-0.46

LayoutConstraint

-0.45

 hysteresis

-0.43

 rosse

-0.43

POSITIVE LOGITS

 position

1.61

 positions

1.61

 Position

1.35

 Positions

1.35

 posisi

1.27

positions

1.26

 jobs

1.22

position

1.22

Position

1.21

 POSITION

1.21

Activations Density 0.250%

references to leadership roles and positions within organizations

No Comments

No Known Activations