INDEX

Explanations

references to locations or conditions, particularly involving 'in' and 'on'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 GenerationType

-0.72

SharedCtor

-0.70

 ujednoznacz

-0.65

 Numerade

-0.65

 Theſe

-0.64

󠁴

-0.59

Aholisi

-0.58

 mourut

-0.58

setViewportView

-0.58

GEBURTSDATUM

-0.57

POSITIVE LOGITS

 فريبيس

0.61

in

0.59

inz

0.54

on

0.53

 draußen

0.50

 pitä

0.47

委员

0.46

at

0.46

 involved

0.46

ggak

0.45

Activations Density 0.417%

references to locations or conditions, particularly involving 'in' and 'on'

No Comments

No Known Activations