INDEX

Explanations

references to retail and business settings

oai_token-act-pair · gpt-3.5-turbo

terms related to retail and occupational references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

zanne

-0.75

 "$:/

-0.72

mson

-0.70

 strawberries

-0.68

wagen

-0.66

 elephant

-0.65

horse

-0.65

 monkeys

-0.65

sta

-0.64

 chimpanzees

-0.64

POSITIVE LOGITS

 Occup

1.86

 Retail

1.74

 Opening

1.64

Occup

1.42

IOC

1.20

 Overse

1.15

Occ

1.08

 Entry

1.06

estate

1.02

Offic

1.01

Activations Density 0.065%

references to retail and business settings

terms related to retail and occupational references

No Comments

No Known Activations