INDEX

Explanations

numerical values and temporal references

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

 autorytatywna

-1.07

thâu

-1.03

haviour

-1.01

vellous

-0.98

defence

-0.97

labour

-0.96

 تضيفلها

-0.94

 Initialise

-0.93

 Enquiries

-0.92

Organiser

-0.92

POSITIVE LOGITS

 statewide

0.60

 utilizes

0.55

 utilizing

0.55

 Statewide

0.54

 sauer

0.51

 utilize

0.50

 Cajun

0.49

0.48

 thru

0.48

LAHOMA

0.47

Activations Density 0.652%

numerical values and temporal references

No Comments

No Known Activations