INDEX

Explanations

mentions of self-driving technology

oai_token-act-pair · gpt-3.5-turbo

terms related to self-driving technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 print

-0.71

Gem

-0.65

Tr

-0.64

 Reyn

-0.63

 round

-0.63

mat

-0.62

sy

-0.61

Pat

-0.61

 repr

-0.60

Tob

-0.59

POSITIVE LOGITS

driving

4.43

driver

1.86

drivers

1.84

 Driving

1.81

Dri

1.71

drive

1.61

 driving

1.61

dri

1.33

 Drivers

1.31

flying

1.25

Activations Density 0.013%

mentions of self-driving technology

terms related to self-driving technology

No Comments

No Known Activations