INDEX

Explanations

references to legal cases and court decisions

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

 myſelf

-1.81

 itſelf

-1.79

 themſelves

-1.63

 Jefus

-1.51

 houſe

-1.47

 Monfieur

-1.45

 himſelf

-1.44

 purpoſe

-1.44

 ſtate

-1.43

^(@)

-1.41

POSITIVE LOGITS

una

0.80

sem

0.79

tr

0.79

lo

0.79

kl

0.78

il

0.78

ios

0.77

Ã

0.77

int

0.77

Activations Density 1.824%

references to legal cases and court decisions

No Comments

No Known Activations