INDEX

Explanations

automobile features and modifications

oai_token-act-pair · gpt-3.5-turbo

terms and components related to automotive modifications and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Merit

-0.93

inventoryQuantity

-0.89

Attempts

-0.86

dule

-0.85

ModLoader

-0.84

genre

-0.80

imester

-0.80

reason

-0.79

prison

-0.79

ebin

-0.78

POSITIVE LOGITS

 adjustable

1.53

 removable

1.47

 rear

1.21

 molded

1.20

 stainless

1.16

 reversible

1.13

 retract

1.12

 angled

1.09

 threaded

1.09

 aluminum

1.08

Activations Density 0.263%

automobile features and modifications

terms and components related to automotive modifications and specifications

No Comments

No Known Activations