INDEX

Explanations

terms related to historical eras

oai_token-act-pair · gpt-3.5-turbo

references to historical time periods or eras

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

liga

-0.91

olulu

-0.88

sie

-0.86

 mathemat

-0.83

eneg

-0.81

iversal

-0.80

enth

-0.78

swer

-0.76

ers

-0.75

cards

-0.75

POSITIVE LOGITS

BILITY

0.74

era

0.73

ffiti

0.67

Äĩ

0.65

isons

0.63

fters

0.62

ocide

0.61

 Antiqu

0.60

ption

0.59

Era

0.59

Activations Density 0.010%

terms related to historical eras

references to historical time periods or eras

No Known Activations