INDEX

Explanations

references to errors and mistakes 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 @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

complexContent

-0.61

windowFixed

-0.52

 AssemblyProduct

-0.51

dubbo

-0.50

Demografía

-0.49

ędziesz

-0.49

urlpatterns

-0.47

 RequestMethod

-0.46

OrBuilder

-0.46

 LoggerFactory

-0.46

POSITIVE LOGITS

 mistake

2.70

 mistakes

2.68

 error

2.56

 errors

2.45

 Mistakes

2.31

 Mistake

2.18

 erreur

2.09

 Errors

2.09

error

2.08

 Error

2.06

Activations Density 1.040%

references to errors and mistakes in various contexts

No Comments

No Known Activations