INDEX

Explanations

isolated segments of code or technical content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

<bos>

-0.80

-0.48

-0.46

-0.44

<eos>

-0.44

-0.42

-0.41

-0.40

POSITIVE LOGITS

 ſeveral

0.84

 Monfieur

0.81

 Theſe

0.80

 itſelf

0.78

 whoſe

0.75

>\<^

0.75

Efq

0.74

^(@)

0.74

 myſelf

0.74

 ་་

0.74

Activations Density 10.248%

isolated segments of code or technical content

No Comments

No Known Activations