INDEX

Explanations

dates written in a specific format

oai_token-act-pair · gpt-3.5-turbo

opening parentheses

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 skyrocket

-0.80

 discrim

-0.77

 ranged

-0.77

 swoop

-0.77

 plummeted

-0.76

 pill

-0.76

 demol

-0.76

 langu

-0.76

 attracted

-0.76

 elevated

-0.74

POSITIVE LOGITS

Photo

1.68

Courtesy

1.54

Published

1.43

credit

1.40

CBC

1.40

AP

1.35

Reuters

1.35

Credit

1.33

photo

1.32

Jonathan

1.31

Activations Density 0.035%

dates written in a specific format

opening parentheses

No Comments

No Known Activations