INDEX

Explanations

connections between concepts or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

entibus

-0.51

Далее

-0.50

jsdelivr

-0.49

 Filed

-0.48

 Some

-0.48

@[+][

-0.48

نجليزية

-0.48

amarca

-0.47

Furthermore

-0.47

*/].

-0.47

POSITIVE LOGITS

autre

1.35

 otro

1.19

 otra

1.16

other

1.11

另一

1.11

 outra

1.10

 another

1.09

 другой

1.04

另一个

1.04

 other

1.04

Activations Density 0.175%

connections between concepts or entities

No Comments

No Known Activations