INDEX

Explanations

named entities, such as names of cities, people, organizations, and dates

oai_token-act-pair · gpt-3.5-turbo

references to specific dates and historical facts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

icter

-0.78

ļéĨĴ

-0.74

 forgetting

-0.73

 takeaway

-0.68

 worrying

-0.68

 tack

-0.67

urances

-0.67

iment

-0.66

 WARN

-0.64

 inexper

-0.63

POSITIVE LOGITS

 originated

0.97

 Originally

0.90

 refers

0.88

 Located

0.87

aka

0.82

 coined

0.82

 Known

0.81

 Became

0.79

 represents

0.75

 Travels

0.75

Activations Density 0.389%

named entities, such as names of cities, people, organizations, and dates

references to specific dates and historical facts

No Comments

No Known Activations