INDEX

Explanations

names of companies or specific products

oai_token-act-pair · gpt-3.5-turbo

proper nouns and technical terms related to specific subjects, such as technology and health

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 âĢº

-0.52

 ..........

-0.50

----

-0.47

taboola

-0.46

-0.45

 ......

-0.45

 Gutierrez

-0.42

MUS

-0.42

Companies

-0.41

...

-0.40

POSITIVE LOGITS

rul

0.50

ultimate

0.47

ailability

0.47

gins

0.47

senal

0.45

ahime

0.44

ULE

0.43

roller

0.43

uterte

0.43

imore

0.42

Activations Density 1.917%

names of companies or specific products

proper nouns and technical terms related to specific subjects, such as technology and health

No Comments

No Known Activations