INDEX

Explanations

specific details or examples related to historical events or circumstances

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

•Layer 6 UMAP region: Mostly-local line at bottom - local

No Comments

Negative Logits

!".

-0.46

'.

-0.45

".[

-0.45

".

-0.43

'."

-0.43

''.

-0.43

.<

-0.43

.'"

-0.42

.""

-0.42

.''.

-0.41

POSITIVE LOGITS

)]

0.43

 foregoing

0.40

?)

0.38

?),

0.37

wealth

0.37

pires

0.35

iosity

0.34

?)

0.34

)?

0.33

)\

0.33

Activations Density 13.433%

specific details or examples related to historical events or circumstances

No Comments

No Known Activations