INDEX

Explanations

references to specific characters and their abilities within a fictional context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

istoitu

-0.98

IntoConstraints

-0.93

+#+#

-0.92

 propOrder

-0.86

dotenv

-0.84

EndGlobalSection

-0.81

 հղումներ

-0.80

Hochspringen

-0.79

ImageContext

-0.78

ArgsConstructor

-0.77

POSITIVE LOGITS

antaranya

0.65

bbene

0.62

 complémentaires

0.60

fæ

0.58

 tartalmaz

0.56

 megfe

0.55

 Theſe

0.55

 bouch

0.55

'>=

0.53

وردار

0.53

Activations Density 1.204%

references to specific characters and their abilities within a fictional context

No Comments

No Known Activations