INDEX

Explanations

specific terms related to products and technologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

Geplaatst

-0.68

initComponents

-0.64

 nahilalakip

-0.60

 defaultstate

-0.59

 snippetHide

-0.58

NgModule

-0.56

 Kompon

-0.53

SuppressMessage

-0.52

RepeatedField

-0.52

 autorytatywna

-0.52

POSITIVE LOGITS

 HasFactory

0.55

vodní

0.52

 تانيه

0.49

참고

0.47

と言えば

0.45

此次

0.45

ഈ

0.45

 tuto

0.45

Хьажоргаш

0.45

这次

0.44

Activations Density 0.402%

specific terms related to products and technologies

No Comments

No Known Activations