INDEX

Explanations

programming or technical terms, particularly in relation to functions and their execution in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

-0.55

ne

-0.48

EAD

-0.45

if

-0.42

all

-0.41

one

-0.41

 fron

-0.40

co

-0.40

POSITIVE LOGITS

 незавершена

1.07

 Мексичка

1.04

 estekak

1.01

 myſelf

0.91

rrggbb

0.89

 EClass

0.87

 nahilalakip

0.86

 transfieras

0.86

 Monfieur

0.85

Portail

0.84

Activations Density 0.256%

programming or technical terms, particularly in relation to functions and their execution in code

No Comments

No Known Activations