INDEX

Explanations

mentions of distances, particularly in meters

oai_token-act-pair · gpt-3.5-turbo

measurements or quantities expressed in metric units

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

NESS

-0.63

 Behavior

-0.62

 psychotic

-0.60

 behav

-0.60

 psycho

-0.59

 Wasteland

-0.56

 fermented

-0.56

 Grateful

-0.56

 Hath

-0.56

IDER

-0.55

POSITIVE LOGITS

obiles

1.19

hz

1.01

umbai

0.98

iles

0.93

ths

0.90

useum

0.89

otor

0.89

ormon

0.87

obil

0.86

Ã¥

0.85

Activations Density 0.030%

mentions of distances, particularly in meters

measurements or quantities expressed in metric units

No Comments

No Known Activations