INDEX

Explanations

statements related to society and individuals within a community

oai_token-act-pair · gpt-3.5-turbo

references to groups of people or entities that are affected by various situations or challenges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Cosponsors

-0.76

iannopoulos

-0.70

illes

-0.67

xtap

-0.66

skirts

-0.64

 brisk

-0.63

ioned

-0.61

charg

-0.61

Haunted

-0.60

 Preferred

-0.59

POSITIVE LOGITS

 purposes

1.22

 sake

1.17

ankind

0.90

 reasons

0.78

 fledgling

0.71

 aspiring

0.70

erning

0.70

 foreseeable

0.69

 onlook

0.68

 policymakers

0.68

Activations Density 0.554%

statements related to society and individuals within a community

references to groups of people or entities that are affected by various situations or challenges

No Comments

No Known Activations