INDEX

Explanations

names or entities related to people

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "ge" as well as related terms or patterns representing age

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

kefeller

-0.77

Interstitial

-0.69

rontal

-0.66

icum

-0.65

TEXT

-0.63

iqueness

-0.63

ABE

-0.62

ework

-0.62

ishment

-0.59

INC

-0.58

POSITIVE LOGITS

hog

1.28

rer

1.24

orge

1.19

rers

1.12

ll

1.12

cko

1.03

vity

1.02

llers

0.97

orget

0.97

eks

0.95

Activations Density 0.038%

names or entities related to people

occurrences of the word "ge" as well as related terms or patterns representing age

No Comments

No Known Activations