INDEX

Explanations

numerical figures in a specific range

oai_token-act-pair · gpt-3.5-turbo

numerical values and statistics

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

advant

-0.77

atorial

-0.67

rade

-0.62

eus

-0.62

FACE

-0.59

arton

-0.59

Else

-0.58

cone

-0.57

INGTON

-0.56

±

-0.55

POSITIVE LOGITS

%.

1.15

 apiece

1.03

%,

1.03

%;

0.92

per

0.85

 tonnes

0.82

 units

0.81

kb

0.80

 litres

0.80

+.

0.79

Activations Density 0.188%

numerical figures in a specific range

numerical values and statistics

No Comments

No Known Activations