INDEX

Explanations

terms related to legal burdens of proof and evidence presentation

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

IntoConstraints

-0.54

 Betracht

-0.54

/***/

-0.53

enet

-0.51

ffindor

-0.50

tagHelper

-0.50

ơn

-0.48

ôtel

-0.48

msub

-0.48

djangoproject

-0.47

POSITIVE LOGITS

 prove

2.21

 proving

2.12

 proof

2.04

 demonstrate

2.00

 demonstrating

2.00

 demostrar

1.96

 demonstrated

1.93

 proves

1.93

 Prove

1.92

 demonstration

1.90

Activations Density 0.942%

terms related to legal burdens of proof and evidence presentation

No Comments

No Known Activations