INDEX

Explanations

proper names likely associated with the name "Rob"

oai_token-act-pair · gpt-3.5-turbo

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

WAYS

-0.67

fu

-0.67

SEE

-0.60

uate

-0.59

SV

-0.58

 sporadic

-0.58

uated

-0.58

 halls

-0.58

RED

-0.57

 paternity

-0.57

POSITIVE LOGITS

bery

1.24

bie

1.17

inson

1.15

otic

1.12

otics

1.05

shaw

1.05

otech

1.05

bers

0.99

bing

0.99

redo

0.99

Activations Density 0.021%

proper names likely associated with the name "Rob"

No Comments

No Known Activations