INDEX

Explanations

locations, especially cities and countries

oai_token-act-pair · gpt-3.5-turbo

locations and geographical references

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ueller

-0.77

osexual

-0.76

":"/

-0.70

ioned

-0.66

obin

-0.65

agine

-0.65

":-

-0.65

 incarn

-0.64

ercise

-0.64

rices

-0.63

POSITIVE LOGITS

 Calif

1.11

 Colo

0.98

 Queens

0.95

Ala

0.95

shire

0.95

 District

0.95

Md

0.93

 County

0.92

 Berks

0.88

 Borough

0.87

Activations Density 0.156%

locations, especially cities and countries

locations and geographical references

No Comments

No Known Activations