INDEX

Explanations

references to 'demo' in various contexts

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

íncia

-0.74

SerializedSize

-0.73

bbene

-0.72

djangoproject

-0.70

newswire

-0.69

harusnya

-0.67

ıll

-0.65

AccessorTable

-0.65

encodeWith

-0.65

jalá

-0.65

POSITIVE LOGITS

 demo

2.43

Dem

2.22

Dem

2.22

 Demo

2.13

dem

2.12

dem

2.00

demo

1.93

 demos

1.89

DEM

1.85

 DEMO

1.84

Activations Density 0.075%

references to 'demo' in various contexts

No Comments

No Known Activations