INDEX

Explanations

phrases related to authorization and hierarchy 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 @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 propOrder

-0.85

RenderAtEndOf

-0.64

 asiatique

-0.60

 Chim

-0.60

PreferredItem

-0.57

 Caballero

-0.53

 otomatig

-0.53

 cliquez

-0.53

ấp

-0.52

 Adic

-0.52

POSITIVE LOGITS

Au

1.80

au

1.71

au

1.70

 audit

1.69

Au

1.67

AU

1.62

 auditing

1.58

AU

1.56

aud

1.56

AUD

1.54

Activations Density 0.410%

phrases related to authorization and hierarchy within organizations

No Comments

No Known Activations