INDEX

Explanations

references to dragons and other mythical creatures, particularly in narratives

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

IsContent

-0.64

pshots

-0.59

RuleContext

-0.57

clable

-0.57

 ujednoznacz

-0.56

 InputDecoration

-0.55

cshtml

-0.53

ứng

-0.53

TagMode

-0.53

prepareStatement

-0.50

POSITIVE LOGITS

 dragon

1.09

 serpent

0.95

 tiger

0.95

 wolf

0.91

 DRAGON

0.90

 Dragon

0.90

Dragon

0.90

 whale

0.90

 elephant

0.89

 lion

0.88

Activations Density 0.319%

references to dragons and other mythical creatures, particularly in narratives

No Comments

No Known Activations