INDEX

Explanations

terms related to legal processes and incarceration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

not

-0.56

ukh

-0.52

ffective

-0.51

-0.49

sa

-0.48

нти

-0.48

 Pacheco

-0.46

 tepat

-0.46

put

-0.45

No

-0.45

POSITIVE LOGITS

ance

2.78

ANCE

2.24

ances

1.86

ANCES

1.30

 ance

1.16

anced

1.15

ancing

1.11

Personendaten

1.00

GOTREF

0.96

 ostavi

0.95

Activations Density 0.775%

terms related to legal processes and incarceration

No Comments

No Known Activations