INDEX

Explanations

the word "body" or variations of it

oai_token-act-pair · gpt-3.5-turbo

references to "somebody" or variations thereof, indicating a focus on people in general

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ring

-0.76

interstitial

-0.71

orses

-0.65

ozo

-0.65

QR

-0.65

eeds

-0.63

otes

-0.63

Ore

-0.61

 precip

-0.61

utenberg

-0.61

POSITIVE LOGITS

 else

1.28

Else

1.12

else

1.11

 Else

1.01

EL

0.85

body

0.82

 alike

0.80

 interviewed

0.76

theless

0.75

 Bastard

0.73

Activations Density 0.033%

the word "body" or variations of it

references to "somebody" or variations thereof, indicating a focus on people in general

No Comments

No Known Activations