INDEX

Explanations

references to a specific name or brand associated with "Ro"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

dė

-0.83

epam

-0.76

 Verdun

-0.74

IDC

-0.71

 evid

-0.71

 vald

-0.70

 Evid

-0.70

digt

-0.67

mika

-0.67

 Schatz

-0.66

POSITIVE LOGITS

Ro

2.22

Ro

2.11

ro

1.75

RO

1.66

ro

1.52

 Rovers

1.49

RO

1.49

 Roch

1.23

 Rober

1.17

 rosette

1.16

Activations Density 0.056%

references to a specific name or brand associated with "Ro"

No Comments

No Known Activations