INDEX

Explanations

details related to product specifications and sizing in reviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

 Politiker

-0.51

Carreira

-0.51

 subsystems

-0.43

 تانيه

-0.43

hty

-0.43

 Roskov

-0.43

protoc

-0.42

 papà

-0.41

Neb

-0.41

 integrand

-0.41

POSITIVE LOGITS

 size

1.05

 sizing

1.03

 sizes

1.03

 Fits

1.01

fit

0.99

 fits

0.98

 fitting

0.95

 Fitting

0.93

fits

0.91

fit

0.90

Activations Density 0.107%

details related to product specifications and sizing in reviews

No Comments

No Known Activations