INDEX

Explanations

keywords related to laboratory settings and experiments

oai_token-act-pair · gpt-3.5-turbo

mentions of laboratories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Vote

-0.80

cut

-0.74

atra

-0.73

rising

-0.70

CHAT

-0.68

generic

-0.68

emption

-0.67

Torrent

-0.67

pend

-0.65

qual

-0.64

POSITIVE LOGITS

rador

1.17

 laboratory

0.96

 laboratories

0.91

 labs

0.91

 chemist

0.89

ysis

0.87

chem

0.87

 Laboratory

0.84

 microbi

0.82

 technician

0.82

Activations Density 0.032%

keywords related to laboratory settings and experiments

mentions of laboratories

No Comments

No Known Activations