INDEX

Explanations

prepositions used with specific nouns or phrases

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a connection or association with various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

itiz

-0.79

iggurat

-0.76

chuk

-0.75

TPP

-0.74

BP

-0.74

ulf

-0.74

hid

-0.72

NESS

-0.71

erella

-0.71

Strange

-0.71

POSITIVE LOGITS

 regard

1.07

 plenty

1.07

 apologies

1.00

 exceptions

0.97

 varying

0.96

 ample

0.90

 some

0.90

 regards

0.89

 fewer

0.88

no

0.88

Activations Density 0.103%

prepositions used with specific nouns or phrases

phrases that indicate a connection or association with various subjects

No Comments

No Known Activations