INDEX

Explanations

specific and detailed technical terms or phrases

oai_token-act-pair · gpt-3.5-turbo

references to various data entities and their relationships

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

enance

-0.73

BIL

-0.70

ophobia

-0.69

 scorn

-0.69

ledge

-0.69

hetamine

-0.67

anus

-0.67

ognitive

-0.67

ynchronous

-0.67

avior

-0.65

POSITIVE LOGITS

 chapters

1.37

 batches

1.36

 sites

1.35

 editions

1.29

 folders

1.29

 stations

1.26

 regions

1.25

 departments

1.23

 projects

1.23

 sessions

1.21

Activations Density 0.434%

specific and detailed technical terms or phrases

references to various data entities and their relationships

No Comments

No Known Activations