INDEX

Explanations

word tokens related to technical devices or equipment

oai_token-act-pair · gpt-3.5-turbo

mentions of various types of "devices"

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

Not in Any Lists

No Comments

Negative Logits

 Nights

-0.91

steen

-0.77

gres

-0.75

ta

-0.74

 tides

-0.68

stad

-0.68

unin

-0.67

 Alban

-0.67

night

-0.67

vo

-0.67

POSITIVE LOGITS

 implanted

0.94

 devices

0.92

 Devices

0.91

 device

0.88

 Device

0.80

 gadget

0.77

 gadgets

0.74

ively

0.73

Registered

0.73

ables

0.72

Activations Density 0.015%

word tokens related to technical devices or equipment

mentions of various types of "devices"

No Comments

No Known Activations