INDEX

Explanations

specific mentions of electronic devices

oai_token-act-pair · gpt-3.5-turbo

references to various devices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

-0.86

stad

-0.85

 Nights

-0.82

gres

-0.71

heit

-0.68

atorium

-0.68

osta

-0.68

ta

-0.67

vind

-0.67

é»Ĵ

-0.67

POSITIVE LOGITS

 devices

1.00

 Devices

0.93

awei

0.85

 device

0.84

 implanted

0.84

devices

0.77

 Device

0.76

 gadgets

0.72

 wallets

0.71

Registered

0.71

Activations Density 0.025%

specific mentions of electronic devices

references to various devices

No Comments

No Known Activations