INDEX

Explanations

references to legislation or legal acts

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

sonian

-0.87

ایج

-0.84

 Marconi

-0.81

 nahilalakip

-0.76

IORITY

-0.76

ROMA

-0.75

vani

-0.74

TopLevel

-0.72

 Brewster

-0.72

 ſou

-0.71

POSITIVE LOGITS

Act

2.28

act

2.21

ACT

2.07

 Acts

2.04

Act

1.99

 acts

1.98

Acts

1.73

act

1.72

ACT

1.67

 ACTS

1.58

Activations Density 0.063%

references to legislation or legal acts

No Comments

No Known Activations