INDEX

Explanations

references to legal and procedural terminology related to cases and evidence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 original

-0.49

original

-0.46

стый

-0.46

 produced

-0.45

output

-0.44

 output

-0.44

grun

-0.43

ltä

-0.43

綿

-0.42

 sfor

-0.42

POSITIVE LOGITS

 regarding

1.00

InjectAttribute

0.99

 Regarding

0.98

 matters

0.97

 privind

0.97

 Tentang

0.97

Concerning

0.97

 dotyczące

0.96

 disambiguazione

0.96

 Concerning

0.95

Activations Density 0.409%

references to legal and procedural terminology related to cases and evidence

No Comments

No Known Activations