INDEX

Explanations

phrases in a specific format ending with "and" followed by a name

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "and."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Normal

-0.66

inse

-0.65

Different

-0.64

lower

-0.64

medi

-0.63

BU

-0.63

hub

-0.63

XP

-0.62

Specific

-0.61

capital

-0.60

POSITIVE LOGITS

 Associates

1.38

 colleagues

1.15

 Kenneth

1.11

 Jennifer

1.10

 Patrick

1.10

 Julie

1.10

 Andrew

1.09

 Jason

1.08

 Michael

1.08

 Jeffrey

1.08

Activations Density 0.090%

phrases in a specific format ending with "and" followed by a name

the repeated use of the word "and."

No Comments

No Known Activations