INDEX

Explanations

I'm sorry, I couldn't find a clear pattern in the activations for Neuron 4

oai_token-act-pair · gpt-3.5-turbo

expressions of moral beliefs and spiritual concepts

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

 frontline

-0.81

uca

-0.79

 defund

-0.74

 freel

-0.73

irtual

-0.72

 streaming

-0.72

 amnesty

-0.70

 targeted

-0.69

 Wallet

-0.69

 wallets

-0.68

POSITIVE LOGITS

Thus

1.21

Therefore

1.17

Moreover

1.09

Nevertheless

1.07

Secondly

1.06

Furthermore

1.05

However

1.02

CONCLUS

1.02

Chapter

1.01

ÂłÂłÂłÂł

1.01

Activations Density 0.575%

I'm sorry, I couldn't find a clear pattern in the activations for Neuron 4

expressions of moral beliefs and spiritual concepts

No Comments

No Known Activations