INDEX

Explanations

references to specific locations or institutions related to educational settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

Pranala

-0.56

 Nantucket

-0.55

 desafío

-0.50

MLLoader

-0.49

 Unito

-0.48

asius

-0.48

 Newark

-0.48

msgTypes

-0.47

 signora

-0.47

skj

-0.46

POSITIVE LOGITS

 Oklahoma

1.49

Oklahoma

1.44

lahoma

1.23

LAHOMA

1.18

 Okla

1.14

 Tulsa

1.11

OK

1.00

Ok

0.94

Tul

0.88

 Edmond

0.86

Activations Density 0.150%

references to specific locations or institutions related to educational settings

No Comments

No Known Activations