INDEX

Explanations

dates and locations mentioned in a document

oai_token-act-pair · gpt-3.5-turbo

financial and numerical data related to events and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

-0.54

[/

-0.53

 Dollars

-0.52

SET

-0.49

 THEN

-0.49

MIN

-0.49

(&

-0.48

VP

-0.46

ISS

-0.46

 queens

-0.46

POSITIVE LOGITS

ennis

0.58

oche

0.57

hran

0.56

comfort

0.55

akh

0.55

igel

0.54

amba

0.53

aff

0.53

arling

0.52

iddled

0.52

Activations Density 0.383%

dates and locations mentioned in a document

financial and numerical data related to events and statistics

No Comments

No Known Activations