INDEX

Explanations

sentences or phrases contrasting different aspects or options

oai_token-act-pair · gpt-3.5-turbo

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

hire

-0.67

ª

-0.65

clud

-0.61

thouse

-0.60

endor

-0.59

aii

-0.58

vest

-0.57

okia

-0.56

orc

-0.55

arag

-0.55

POSITIVE LOGITS

depending

1.76

 Either

1.47

 respectively

1.41

 whichever

1.38

 depending

1.38

 Both

1.26

Either

1.20

Both

1.14

ichever

1.08

 Whatever

1.07

Activations Density 0.902%

sentences or phrases contrasting different aspects or options

No Comments

No Known Activations