INDEX

Explanations

positive attributes or impactful events

oai_token-act-pair · gpt-3.5-turbo

expressions of good news and positive developments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ĸļ

-1.16

ICLE

-0.87

hyde

-0.85

emale

-0.85

bsite

-0.81

dq

-0.77

chel

-0.75

externalActionCode

-0.74

athlon

-0.73

arcity

-0.72

POSITIVE LOGITS

 surprises

1.21

 goodies

1.15

 tricks

1.15

 stuff

1.06

 caveats

1.03

 shenanigans

1.03

 gems

1.00

 things

0.98

 pointers

0.97

 twists

0.97

Activations Density 0.202%

positive attributes or impactful events

expressions of good news and positive developments

No Comments

No Known Activations