INDEX

Explanations

words related to decoration or being adorned

oai_token-act-pair · gpt-3.5-turbo

terms related to decoration and embellishment

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FS

-0.79

FTA

-0.75

PU

-0.72

FER

-0.70

GH

-0.69

RS

-0.69

ffic

-0.69

demand

-0.68

appro

-0.67

LS

-0.66

POSITIVE LOGITS

 decorated

1.39

 decoration

1.38

 decorations

1.38

 decor

1.05

nesday

0.90

ocument

0.89

rette

0.83

dinand

0.83

 colours

0.82

issance

0.81

Activations Density 0.006%

words related to decoration or being adorned

terms related to decoration and embellishment

No Comments

No Known Activations