INDEX

Explanations

phrases related to instructions or steps to take

oai_token-act-pair · gpt-3.5-turbo

references to the concept of togetherness or unity

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

pse

-0.47

 outburst

-0.47

sov

-0.46

 Enhancement

-0.44

best

-0.44

 hordes

-0.43

 Redux

-0.43

thing

-0.43

eport

-0.42

etheus

-0.42

POSITIVE LOGITS

++)

0.63

]);

0.56

 trusting

0.55

 comfortable

0.52

dL

0.52

nosis

0.51

cas

0.50

));

0.49

pret

0.49

imate

0.48

Activations Density 0.843%

phrases related to instructions or steps to take

references to the concept of togetherness or unity

No Comments

No Known Activations