INDEX

Explanations

device-related terms and identifiers

oai_token-act-pair · gpt-3.5-turbo

references to electronic devices

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

steen

-0.88

 Nights

-0.76

gres

-0.75

stad

-0.75

heit

-0.74

atorium

-0.70

hound

-0.70

 Lutheran

-0.67

 tides

-0.66

 Kern

-0.66

POSITIVE LOGITS

 devices

0.97

 Devices

0.88

 device

0.81

 implanted

0.81

awei

0.78

 Device

0.78

 manufacturers

0.76

 manufacturer

0.74

devices

0.73

 interfaces

0.72

Activations Density 0.030%

device-related terms and identifiers

references to electronic devices

No Comments

No Known Activations