INDEX

Explanations

references to events, particularly awards and accomplishments, with a focus on historical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 propOrder

-0.77

WindowConstants

-0.73

 Pring

-0.71

MigrationBuilder

-0.70

 Segurança

-0.67

 незавершена

-0.67

DataAnnotations

-0.66

 Viter

-0.65

UnknownFields

-0.64

mybatisplus

-0.64

POSITIVE LOGITS

äksi

0.60

 Cohen

0.59

erf

0.57

the

0.56

 Schwartz

0.54

Jim

0.54

 four

0.53

 internetowa

0.51

elman

0.51

 five

0.51

Activations Density 0.210%

references to events, particularly awards and accomplishments, with a focus on historical context

No Comments

No Known Activations