INDEX

Explanations

recurring patterns of system configurations and the term 'express'

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-0.85

 pleaſure

-0.84

fucker

-0.82

 purpoſe

-0.82

 himſelf

-0.82

 poffe

-0.80

TemporalType

-0.79

OOTDTY

-0.77

$_"

-0.75

 Jefus

-0.72

POSITIVE LOGITS

express

0.99

 express

0.84

 expresa

0.68

 expres

0.65

 Express

0.60

Express

0.59

Configuration

0.57

 EXPRESS

0.57

 parcel

0.57

 Sandy

0.55

Activations Density 0.095%

recurring patterns of system configurations and the term 'express'

No Comments

No Known Activations