INDEX

Explanations

phrases related to hard work, determination, and collaboration

oai_token-act-pair · gpt-3.5-turbo

themes related to love, collaboration, and perseverance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ocry

-0.85

earable

-0.75

ghazi

-0.72

anamo

-0.72

ricted

-0.71

rongh

-0.70

adden

-0.67

achelor

-0.66

arer

-0.64

LCS

-0.64

POSITIVE LOGITS

 ingenuity

1.22

 intervention

1.06

 luck

0.99

 persever

0.96

 interven

0.90

 diligent

0.89

 efforts

0.89

 intervened

0.88

 savvy

0.87

 deft

0.85

Activations Density 0.666%

phrases related to hard work, determination, and collaboration

themes related to love, collaboration, and perseverance

No Comments

No Known Activations