INDEX

Explanations

phrases or terms related to legal terminology and arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

-0.82

ness

-0.81

ings

-0.75

-0.68

</b>

-0.66

ing

-0.65

est

-0.64

 Ches

-0.63

-0.62

 OkHttpClient

-0.62

POSITIVE LOGITS

 myſelf

1.11

 themſelves

1.10

ViewFeatures

1.09

uate

1.04

ATED

1.01

 itſelf

1.00

uminate

0.97

 δὲ

0.97

ated

0.94

TintMode

0.94

Activations Density 0.616%

phrases or terms related to legal terminology and arguments

No Comments

No Known Activations