INDEX

Explanations

references to legal cases, statutes, or judicial decisions

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

存于互联网档案馆

-0.86

 Spraw

-0.68

 يتيمه

-0.67

 متعلقه

-0.67

 photocopying

-0.66

ing

-0.65

 Acerca

-0.63

 Luci

-0.61

✨:

-0.61

ING

-0.60

POSITIVE LOGITS

 ModelRenderer

0.86

ssysteme

0.81

cloth

0.77

repor

0.73

RMS

0.73

Nolan

0.72

 Irán

0.72

 gynnwys

0.70

 Shields

0.69

agisse

0.69

Activations Density 2.012%

references to legal cases, statutes, or judicial decisions

No Comments

No Known Activations