INDEX

Explanations

references to legal entities or roles within a legal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 resourceCulture

-1.06

 Infórmanos

-1.02

########.

-1.00

 disambiguazione

-1.00

expandindo

-0.99

aarrggbb

-0.97

AddTagHelper

-0.97

 defaultstate

-0.93

featureID

-0.90

 nakalista

-0.89

POSITIVE LOGITS

0.92

in

0.59

the

0.57

↵

0.55

0.51

to

0.50

↵↵

0.50

The

0.50

0.49

Activations Density 0.761%

references to legal entities or roles within a legal context

No Comments

No Known Activations