INDEX

Explanations

phrases including the abbreviation "SA" followed by a numerical value

oai_token-act-pair · gpt-3.5-turbo

occurrences of the acronym "SA" related to specific contexts or entities

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

ysis

-0.83

tons

-0.76

ships

-0.73

lace

-0.71

naire

-0.68

naires

-0.67

acles

-0.63

hang

-0.62

papers

-0.62

storms

-0.61

POSITIVE LOGITS

VE

1.28

ven

1.05

ULT

1.03

BILITIES

0.95

FE

0.94

ILS

0.90

plings

0.89

BILITY

0.89

vant

0.89

ccess

0.88

Activations Density 0.022%

phrases including the abbreviation "SA" followed by a numerical value

occurrences of the acronym "SA" related to specific contexts or entities

No Comments

No Known Activations