INDEX

Explanations

references to self-driving technology or autonomous vehicles

oai_token-act-pair · gpt-3.5-turbo

terms related to self-driving and autonomous vehicles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ym

-0.69

nee

-0.69

AMI

-0.65

ema

-0.65

Ã©n

-0.64

wick

-0.64

olith

-0.63

eon

-0.63

çĦ

-0.62

adian

-0.62

POSITIVE LOGITS

driving

1.30

 algorithms

0.79

ullivan

0.75

 Lyft

0.74

ragon

0.73

quartered

0.73

 impaired

0.72

 engineer

0.71

 driving

0.71

onomous

0.71

Activations Density 0.021%

references to self-driving technology or autonomous vehicles

terms related to self-driving and autonomous vehicles

No Comments

No Known Activations