INDEX

Explanations

references to the interior of vehicles or spaces

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

UnknownFieldSet

-1.04

ⓧ

-0.88

 Cuer

-0.81

ſelf

-0.77

 Pergamon

-0.76

 pleaſure

-0.75

SpringBootTest

-0.75

 Sima

-0.75

 purpoſe

-0.74

ſelves

-0.71

POSITIVE LOGITS

 paragraph

0.98

paragraph

0.92

 Paragraph

0.79

 paragraphs

0.78

Paragraph

0.77

paragraphs

0.74

 bred

0.69

 soins

0.67

 breed

0.66

 masa

0.64

Activations Density 0.049%

references to the interior of vehicles or spaces

No Comments

No Known Activations