INDEX

Explanations

phrases involving the status or condition of individuals

oai_token-act-pair · gpt-3.5-turbo

the phrase "people who are" indicating discussions about individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Solution

-0.72

pedia

-0.69

 Which

-0.68

 Inventory

-0.67

ization

-0.66

 Exit

-0.64

imation

-0.63

aneous

-0.62

 cancellation

-0.62

 Entry

-0.62

POSITIVE LOGITS

 accustomed

0.85

 addicted

0.84

wolves

0.84

 supposed

0.83

 intimately

0.81

 blinded

0.79

 acquainted

0.77

 interested

0.77

 fluent

0.77

held

0.75

Activations Density 0.138%

phrases involving the status or condition of individuals

the phrase "people who are" indicating discussions about individuals or groups

No Comments

No Known Activations