INDEX

Explanations

events related to achievements and performance in competitive contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Personendaten

-0.60

 مشين

-0.52

Cyfeiriadau

-0.52

 initComponents

-0.51

 légende

-0.51

 cerevisiae

-0.48

 wherefore

-0.46

Referanser

-0.46

IsMutable

-0.45

 ویکی‌پدیا

-0.44

POSITIVE LOGITS

igshid

0.72

AddTagHelper

0.66

AutoScaleMode

0.61

Xna

0.58

 onCreateView

0.57

ształ

0.54

UnknownFields

0.54

ãng

0.53

例句

0.53

Traduction

0.53

Activations Density 0.196%

events related to achievements and performance in competitive contexts

No Comments

No Known Activations