INDEX

Explanations

I'm sorry, but the provided text does not offer enough information for making a reliable analysis of what neuron 4 is looking for

oai_token-act-pair · gpt-3.5-turbo

terms related to political power and its dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

OM

-0.67

 surprises

-0.63

OTOS

-0.60

omas

-0.58

 Rodrig

-0.58

È

-0.57

 conscience

-0.57

hift

-0.56

ovember

-0.56

love

-0.55

POSITIVE LOGITS

ping

1.72

ped

1.63

ps

1.46

pers

1.43

py

1.39

1.37

per

1.32

pel

1.29

pit

1.27

pter

1.24

Activations Density 0.084%

I'm sorry, but the provided text does not offer enough information for making a reliable analysis of what neuron 4 is looking for

terms related to political power and its dynamics

No Comments

No Known Activations