INDEX

Explanations

technical or programming-related terms and symbols, particularly those associated with errors or exceptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 فريبيس

-0.67

 faſt

-0.58

LookAnd

-0.55

+#+#

-0.55

 purpoſe

-0.54

reportWebVitals

-0.52

 fevere

-0.52

 spits

-0.51

äfts

-0.51

Efq

-0.51

POSITIVE LOGITS

GEBURTSDATUM

0.78

XmlAccessorType

0.74

Personendaten

0.71

richTextPanel

0.65

tonsoft

0.64

لينكات

0.63

Einzelnachweise

0.62

andExpect

0.61

peq

0.61

WireFormatLite

0.57

Activations Density 0.029%

technical or programming-related terms and symbols, particularly those associated with errors or exceptions

No Comments

No Known Activations