INDEX

Explanations

phrases related to comparison or contrast

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, particularly commas, indicating list-like or complex sentence structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

aven

-0.56

.--

-0.54

orn

-0.54

 Latter

-0.53

 Respons

-0.53

lor

-0.52

"...

-0.52

lord

-0.50

:(

-0.50

reth

-0.50

POSITIVE LOGITS

 albeit

1.00

 namely

0.91

aka

0.81

 preferably

0.81

Jr

0.70

emort

0.68

 somew

0.66

albeit

0.65

 whereby

0.65

utherford

0.65

Activations Density 0.472%

phrases related to comparison or contrast

punctuation marks, particularly commas, indicating list-like or complex sentence structures

No Comments

No Known Activations