INDEX

Explanations

words related to legal actions and proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iness

-0.70

℉

-0.68

pheny

-0.67

 jura

-0.66

TagHelper

-0.65

Previews

-0.64

 Réunion

-0.63

 setInterval

-0.63

 Divis

-0.63

 interpre

-0.63

POSITIVE LOGITS

ated

1.19

ates

1.19

ate

1.17

ATE

1.16

ATED

1.14

ATES

1.12

uminate

1.10

uate

1.08

nate

1.05

ating

1.04

Activations Density 0.337%

words related to legal actions and proceedings

No Comments

No Known Activations