INDEX

Explanations

terms related to American entities such as organizations, locations, and concepts

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ValueGenerated

-0.59

userdetails

-0.57

 BoxFit

-0.56

resizeMode

-0.55

bootstrapcdn

-0.53

LabelTagHelper

-0.52

PositiveButton

-0.51

rmtree

-0.51

EndInit

-0.51

RunAsync

-0.50

POSITIVE LOGITS

 Amé

1.37

 Châ

1.31

Juf

1.18

 Godt

1.18

 Méri

1.16

 Sinal

1.13

 Áng

1.12

 Mlle

1.12

Mâ

1.11

 Román

1.11

Activations Density 0.091%

terms related to American entities such as organizations, locations, and concepts

No Comments

No Known Activations