INDEX

Explanations

terms related to electrical engineering

oai_token-act-pair · gpt-3.5-turbo

terms related to electrical engineering

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

itia

-0.99

naire

-0.96

lain

-0.75

 Haku

-0.74

chens

-0.74

heimer

-0.73

-0.72

 Connor

-0.70

 Cherokee

-0.70

naires

-0.69

POSITIVE LOGITS

 electrical

1.05

 wiring

1.03

 impedance

1.01

 circuitry

0.98

 circuits

0.98

 stimulation

0.96

 engineering

0.96

 electricity

0.94

 conduc

0.93

 pulses

0.93

Activations Density 0.009%

terms related to electrical engineering

terms related to electrical engineering

No Known Activations