INDEX

Explanations

references to timekeeping devices or systems

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

 ApiException

-0.60

CodeAttribute

-0.56

 Rioja

-0.55

xically

-0.55

ually

-0.55

లాలు

-0.54

{%

-0.52

AddTagHelper

-0.52

icago

-0.51

 tabindex

-0.51

POSITIVE LOGITS

 warrant

0.87

 warrants

0.83

WriteTagHelper

0.82

warrant

0.80

 clock

0.74

ChildScrollView

0.71

 Warrant

0.71

 WARRANT

0.70

ymce

0.68

 Clock

0.68

Activations Density 0.066%

references to timekeeping devices or systems

No Comments

No Known Activations