INDEX

Explanations

author names

oai_token-act-pair · gpt-3.5-turbo

mentions of authorship or authors

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

ttes

-0.79

EMS

-0.75

 Pist

-0.70

Peb

-0.70

romy

-0.69

ll

-0.68

 Nicaragua

-0.68

ints

-0.65

 Bottle

-0.65

 Blasio

-0.64

POSITIVE LOGITS

itative

1.44

itatively

1.22

itarian

1.21

itism

0.86

Author

0.86

gements

0.85

essee

0.83

izations

0.82

itar

0.82

ity

0.81

Activations Density 0.015%

author names

mentions of authorship or authors

No Known Activations