INDEX

Explanations

locations and geographic references within a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personendaten

-0.54

zati

-0.53

zzá

-0.51

rovnik

-0.51

RTGC

-0.50

mployment

-0.49

GEBURTSDATUM

-0.48

atoire

-0.47

PYX

-0.47

aband

-0.46

POSITIVE LOGITS

Спасылкі

0.63

Véxase

0.58

ioneers

0.53

ParallelGroup

0.51

 تضيفلها

0.49

±

0.49

rainy

0.49

ających

0.49

("~/

0.47

lippe

0.47

Activations Density 0.112%

locations and geographic references within a text

No Comments

No Known Activations