INDEX

Explanations

keywords related to having various types of access to something

oai_token-act-pair · gpt-3.5-turbo

references to access in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Kern

-0.76

 farewell

-0.66

kos

-0.60

 grandmother

-0.59

-0.56

Jou

-0.56

 circling

-0.55

 colleague

-0.55

 occurrence

-0.55

 Zeit

-0.55

POSITIVE LOGITS

ibly

1.26

ibility

1.26

ible

1.10

ioned

1.03

 thereto

1.00

ibilities

0.99

ibl

0.91

ion

0.85

ions

0.84

IBLE

0.81

Activations Density 0.033%

keywords related to having various types of access to something

references to access in various contexts

No Comments

No Known Activations